cpython/Doc/api/newtypes.tex

1702 lines
73 KiB
TeX

\chapter{Object Implementation Support \label{newTypes}}
This chapter describes the functions, types, and macros used when
defining new object types.
\section{Allocating Objects on the Heap
\label{allocating-objects}}
\begin{cfuncdesc}{PyObject*}{_PyObject_New}{PyTypeObject *type}
\end{cfuncdesc}
\begin{cfuncdesc}{PyVarObject*}{_PyObject_NewVar}{PyTypeObject *type, int size}
\end{cfuncdesc}
\begin{cfuncdesc}{void}{_PyObject_Del}{PyObject *op}
\end{cfuncdesc}
\begin{cfuncdesc}{PyObject*}{PyObject_Init}{PyObject *op,
PyTypeObject *type}
Initialize a newly-allocated object \var{op} with its type and
initial reference. Returns the initialized object. If \var{type}
indicates that the object participates in the cyclic garbage
detector, it is added to the detector's set of observed objects.
Other fields of the object are not affected.
\end{cfuncdesc}
\begin{cfuncdesc}{PyVarObject*}{PyObject_InitVar}{PyVarObject *op,
PyTypeObject *type, int size}
This does everything \cfunction{PyObject_Init()} does, and also
initializes the length information for a variable-size object.
\end{cfuncdesc}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_New}{TYPE, PyTypeObject *type}
Allocate a new Python object using the C structure type \var{TYPE}
and the Python type object \var{type}. Fields not defined by the
Python object header are not initialized; the object's reference
count will be one. The size of the memory
allocation is determined from the \member{tp_basicsize} field of the
type object.
\end{cfuncdesc}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_NewVar}{TYPE, PyTypeObject *type,
int size}
Allocate a new Python object using the C structure type \var{TYPE}
and the Python type object \var{type}. Fields not defined by the
Python object header are not initialized. The allocated memory
allows for the \var{TYPE} structure plus \var{size} fields of the
size given by the \member{tp_itemsize} field of \var{type}. This is
useful for implementing objects like tuples, which are able to
determine their size at construction time. Embedding the array of
fields into the same allocation decreases the number of allocations,
improving the memory management efficiency.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{PyObject_Del}{PyObject *op}
Releases memory allocated to an object using
\cfunction{PyObject_New()} or \cfunction{PyObject_NewVar()}. This
is normally called from the \member{tp_dealloc} handler specified in
the object's type. The fields of the object should not be accessed
after this call as the memory is no longer a valid Python object.
\end{cfuncdesc}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_NEW}{TYPE, PyTypeObject *type}
Macro version of \cfunction{PyObject_New()}, to gain performance at
the expense of safety. This does not check \var{type} for a \NULL{}
value.
\end{cfuncdesc}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_NEW_VAR}{TYPE, PyTypeObject *type,
int size}
Macro version of \cfunction{PyObject_NewVar()}, to gain performance
at the expense of safety. This does not check \var{type} for a
\NULL{} value.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{PyObject_DEL}{PyObject *op}
Macro version of \cfunction{PyObject_Del()}.
\end{cfuncdesc}
\begin{cfuncdesc}{PyObject*}{Py_InitModule}{char *name,
PyMethodDef *methods}
Create a new module object based on a name and table of functions,
returning the new module object.
\versionchanged[Older versions of Python did not support \NULL{} as
the value for the \var{methods} argument]{2.3}
\end{cfuncdesc}
\begin{cfuncdesc}{PyObject*}{Py_InitModule3}{char *name,
PyMethodDef *methods,
char *doc}
Create a new module object based on a name and table of functions,
returning the new module object. If \var{doc} is non-\NULL, it will
be used to define the docstring for the module.
\versionchanged[Older versions of Python did not support \NULL{} as
the value for the \var{methods} argument]{2.3}
\end{cfuncdesc}
\begin{cfuncdesc}{PyObject*}{Py_InitModule4}{char *name,
PyMethodDef *methods,
char *doc, PyObject *self,
int apiver}
Create a new module object based on a name and table of functions,
returning the new module object. If \var{doc} is non-\NULL, it will
be used to define the docstring for the module. If \var{self} is
non-\NULL, it will passed to the functions of the module as their
(otherwise \NULL) first parameter. (This was added as an
experimental feature, and there are no known uses in the current
version of Python.) For \var{apiver}, the only value which should
be passed is defined by the constant \constant{PYTHON_API_VERSION}.
\note{Most uses of this function should probably be using
the \cfunction{Py_InitModule3()} instead; only use this if you are
sure you need it.}
\versionchanged[Older versions of Python did not support \NULL{} as
the value for the \var{methods} argument]{2.3}
\end{cfuncdesc}
DL_IMPORT
\begin{cvardesc}{PyObject}{_Py_NoneStruct}
Object which is visible in Python as \code{None}. This should only
be accessed using the \code{Py_None} macro, which evaluates to a
pointer to this object.
\end{cvardesc}
\section{Common Object Structures \label{common-structs}}
There are a large number of structures which are used in the
definition of object types for Python. This section describes these
structures and how they are used.
All Python objects ultimately share a small number of fields at the
beginning of the object's representation in memory. These are
represented by the \ctype{PyObject} and \ctype{PyVarObject} types,
which are defined, in turn, by the expansions of some macros also
used, whether directly or indirectly, in the definition of all other
Python objects.
\begin{ctypedesc}{PyObject}
All object types are extensions of this type. This is a type which
contains the information Python needs to treat a pointer to an
object as an object. In a normal ``release'' build, it contains
only the objects reference count and a pointer to the corresponding
type object. It corresponds to the fields defined by the
expansion of the \code{PyObject_HEAD} macro.
\end{ctypedesc}
\begin{ctypedesc}{PyVarObject}
This is an extension of \ctype{PyObject} that adds the
\member{ob_size} field. This is only used for objects that have
some notion of \emph{length}. This type does not often appear in
the Python/C API. It corresponds to the fields defined by the
expansion of the \code{PyObject_VAR_HEAD} macro.
\end{ctypedesc}
These macros are used in the definition of \ctype{PyObject} and
\ctype{PyVarObject}:
\begin{csimplemacrodesc}{PyObject_HEAD}
This is a macro which expands to the declarations of the fields of
the \ctype{PyObject} type; it is used when declaring new types which
represent objects without a varying length. The specific fields it
expands to depend on the definition of
\csimplemacro{Py_TRACE_REFS}. By default, that macro is not
defined, and \csimplemacro{PyObject_HEAD} expands to:
\begin{verbatim}
int ob_refcnt;
PyTypeObject *ob_type;
\end{verbatim}
When \csimplemacro{Py_TRACE_REFS} is defined, it expands to:
\begin{verbatim}
PyObject *_ob_next, *_ob_prev;
int ob_refcnt;
PyTypeObject *ob_type;
\end{verbatim}
\end{csimplemacrodesc}
\begin{csimplemacrodesc}{PyObject_VAR_HEAD}
This is a macro which expands to the declarations of the fields of
the \ctype{PyVarObject} type; it is used when declaring new types which
represent objects with a length that varies from instance to
instance. This macro always expands to:
\begin{verbatim}
PyObject_HEAD
int ob_size;
\end{verbatim}
Note that \csimplemacro{PyObject_HEAD} is part of the expansion, and
that it's own expansion varies depending on the definition of
\csimplemacro{Py_TRACE_REFS}.
\end{csimplemacrodesc}
PyObject_HEAD_INIT
\begin{ctypedesc}{PyCFunction}
Type of the functions used to implement most Python callables in C.
Functions of this type take two \ctype{PyObject*} parameters and
return one such value. If the return value is \NULL, an exception
shall have been set. If not \NULL, the return value is interpreted
as the return value of the function as exposed in Python. The
function must return a new reference.
\end{ctypedesc}
\begin{ctypedesc}{PyMethodDef}
Structure used to describe a method of an extension type. This
structure has four fields:
\begin{tableiii}{l|l|l}{member}{Field}{C Type}{Meaning}
\lineiii{ml_name}{char *}{name of the method}
\lineiii{ml_meth}{PyCFunction}{pointer to the C implementation}
\lineiii{ml_flags}{int}{flag bits indicating how the call should be
constructed}
\lineiii{ml_doc}{char *}{points to the contents of the docstring}
\end{tableiii}
\end{ctypedesc}
The \member{ml_meth} is a C function pointer. The functions may be of
different types, but they always return \ctype{PyObject*}. If the
function is not of the \ctype{PyCFunction}, the compiler will require
a cast in the method table. Even though \ctype{PyCFunction} defines
the first parameter as \ctype{PyObject*}, it is common that the method
implementation uses a the specific C type of the \var{self} object.
The \member{ml_flags} field is a bitfield which can include the
following flags. The individual flags indicate either a calling
convention or a binding convention. Of the calling convention flags,
only \constant{METH_VARARGS} and \constant{METH_KEYWORDS} can be
combined (but note that \constant{METH_KEYWORDS} alone is equivalent
to \code{\constant{METH_VARARGS} | \constant{METH_KEYWORDS}}).
Any of the calling convention flags can be combined with a
binding flag.
\begin{datadesc}{METH_VARARGS}
This is the typical calling convention, where the methods have the
type \ctype{PyCFunction}. The function expects two
\ctype{PyObject*} values. The first one is the \var{self} object for
methods; for module functions, it has the value given to
\cfunction{Py_InitModule4()} (or \NULL{} if
\cfunction{Py_InitModule()} was used). The second parameter
(often called \var{args}) is a tuple object representing all
arguments. This parameter is typically processed using
\cfunction{PyArg_ParseTuple()} or \cfunction{PyArg_UnpackTuple}.
\end{datadesc}
\begin{datadesc}{METH_KEYWORDS}
Methods with these flags must be of type
\ctype{PyCFunctionWithKeywords}. The function expects three
parameters: \var{self}, \var{args}, and a dictionary of all the
keyword arguments. The flag is typically combined with
\constant{METH_VARARGS}, and the parameters are typically processed
using \cfunction{PyArg_ParseTupleAndKeywords()}.
\end{datadesc}
\begin{datadesc}{METH_NOARGS}
Methods without parameters don't need to check whether arguments are
given if they are listed with the \constant{METH_NOARGS} flag. They
need to be of type \ctype{PyCFunction}. When used with object
methods, the first parameter is typically named \code{self} and will
hold a reference to the object instance. In all cases the second
parameter will be \NULL.
\end{datadesc}
\begin{datadesc}{METH_O}
Methods with a single object argument can be listed with the
\constant{METH_O} flag, instead of invoking
\cfunction{PyArg_ParseTuple()} with a \code{"O"} argument. They have
the type \ctype{PyCFunction}, with the \var{self} parameter, and a
\ctype{PyObject*} parameter representing the single argument.
\end{datadesc}
\begin{datadesc}{METH_OLDARGS}
This calling convention is deprecated. The method must be of type
\ctype{PyCFunction}. The second argument is \NULL{} if no arguments
are given, a single object if exactly one argument is given, and a
tuple of objects if more than one argument is given. There is no
way for a function using this convention to distinguish between a
call with multiple arguments and a call with a tuple as the only
argument.
\end{datadesc}
These two constants are not used to indicate the calling convention
but the binding when use with methods of classes. These may not be
used for functions defined for modules. At most one of these flags
may be set for any given method.
\begin{datadesc}{METH_CLASS}
The method will be passed the type object as the first parameter
rather than an instance of the type. This is used to create
\emph{class methods}, similar to what is created when using the
\function{classmethod()}\bifuncindex{classmethod} built-in
function.
\versionadded{2.3}
\end{datadesc}
\begin{datadesc}{METH_STATIC}
The method will be passed \NULL{} as the first parameter rather than
an instance of the type. This is used to create \emph{static
methods}, similar to what is created when using the
\function{staticmethod()}\bifuncindex{staticmethod} built-in
function.
\versionadded{2.3}
\end{datadesc}
One other constant controls whether a method is loaded in place of
another definition with the same method name.
\begin{datadesc}{METH_COEXIST}
The method will be loaded in place of existing definitions. Without
\var{METH_COEXIST}, the default is to skip repeated definitions. Since
slot wrappers are loaded before the method table, the existence of a
\var{sq_contains} slot, for example, would generate a wrapped method
named \method{__contains__()} and preclude the loading of a
corresponding PyCFunction with the same name. With the flag defined,
the PyCFunction will be loaded in place of the wrapper object and will
co-exist with the slot. This is helpful because calls to PyCFunctions
are optimized more than wrapper object calls.
\versionadded{2.4}
\end{datadesc}
\begin{cfuncdesc}{PyObject*}{Py_FindMethod}{PyMethodDef table[],
PyObject *ob, char *name}
Return a bound method object for an extension type implemented in
C. This can be useful in the implementation of a
\member{tp_getattro} or \member{tp_getattr} handler that does not
use the \cfunction{PyObject_GenericGetAttr()} function.
\end{cfuncdesc}
\section{Type Objects \label{type-structs}}
Perhaps one of the most important structures of the Python object
system is the structure that defines a new type: the
\ctype{PyTypeObject} structure. Type objects can be handled using any
of the \cfunction{PyObject_*()} or \cfunction{PyType_*()} functions,
but do not offer much that's interesting to most Python applications.
These objects are fundamental to how objects behave, so they are very
important to the interpreter itself and to any extension module that
implements new types.
Type objects are fairly large compared to most of the standard types.
The reason for the size is that each type object stores a large number
of values, mostly C function pointers, each of which implements a
small part of the type's functionality. The fields of the type object
are examined in detail in this section. The fields will be described
in the order in which they occur in the structure.
Typedefs:
unaryfunc, binaryfunc, ternaryfunc, inquiry, coercion, intargfunc,
intintargfunc, intobjargproc, intintobjargproc, objobjargproc,
destructor, freefunc, printfunc, getattrfunc, getattrofunc, setattrfunc,
setattrofunc, cmpfunc, reprfunc, hashfunc
The structure definition for \ctype{PyTypeObject} can be found in
\file{Include/object.h}. For convenience of reference, this repeats
the definition found there:
\verbatiminput{typestruct.h}
The type object structure extends the \ctype{PyVarObject} structure.
The \member{ob_size} field is used for dynamic types (created
by \function{type_new()}, usually called from a class statement).
Note that \cdata{PyType_Type} (the metatype) initializes
\member{tp_itemsize}, which means that its instances (i.e. type
objects) \emph{must} have the \member{ob_size} field.
\begin{cmemberdesc}{PyObject}{PyObject*}{_ob_next}
\cmemberline{PyObject}{PyObject*}{_ob_prev}
These fields are only present when the macro \code{Py_TRACE_REFS} is
defined. Their initialization to \NULL{} is taken care of by the
\code{PyObject_HEAD_INIT} macro. For statically allocated objects,
these fields always remain \NULL. For dynamically allocated
objects, these two fields are used to link the object into a
doubly-linked list of \emph{all} live objects on the heap. This
could be used for various debugging purposes; currently the only use
is to print the objects that are still alive at the end of a run
when the environment variable \envvar{PYTHONDUMPREFS} is set.
These fields are not inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyObject}{int}{ob_refcnt}
This is the type object's reference count, initialized to \code{1}
by the \code{PyObject_HEAD_INIT} macro. Note that for statically
allocated type objects, the type's instances (objects whose
\member{ob_type} points back to the type) do \emph{not} count as
references. But for dynamically allocated type objects, the
instances \emph{do} count as references.
This field is not inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyObject}{PyTypeObject*}{ob_type}
This is the type's type, in other words its metatype. It is
initialized by the argument to the \code{PyObject_HEAD_INIT} macro,
and its value should normally be \code{\&PyType_Type}. However, for
dynamically loadable extension modules that must be usable on
Windows (at least), the compiler complains that this is not a valid
initializer. Therefore, the convention is to pass \NULL{} to the
\code{PyObject_HEAD_INIT} macro and to initialize this field
explicitly at the start of the module's initialization function,
before doing anything else. This is typically done like this:
\begin{verbatim}
Foo_Type.ob_type = &PyType_Type;
\end{verbatim}
This should be done before any instances of the type are created.
\cfunction{PyType_Ready()} checks if \member{ob_type} is \NULL, and
if so, initializes it: in Python 2.2, it is set to
\code{\&PyType_Type}; in Python 2.2.1 and later it is
initialized to the \member{ob_type} field of the base class.
\cfunction{PyType_Ready()} will not change this field if it is
non-zero.
In Python 2.2, this field is not inherited by subtypes. In 2.2.1,
and in 2.3 and beyond, it is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyVarObject}{int}{ob_size}
For statically allocated type objects, this should be initialized
to zero. For dynamically allocated type objects, this field has a
special internal meaning.
This field is not inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{char*}{tp_name}
Pointer to a NUL-terminated string containing the name of the type.
For types that are accessible as module globals, the string should
be the full module name, followed by a dot, followed by the type
name; for built-in types, it should be just the type name. If the
module is a submodule of a package, the full package name is part of
the full module name. For example, a type named \class{T} defined
in module \module{M} in subpackage \module{Q} in package \module{P}
should have the \member{tp_name} initializer \code{"P.Q.M.T"}.
For dynamically allocated type objects, this should just be the type
name, and the module name explicitly stored in the type dict as the
value for key \code{'__module__'}.
For statically allocated type objects, the tp_name field should
contain a dot. Everything before the last dot is made accessible as
the \member{__module__} attribute, and everything after the last dot
is made accessible as the \member{__name__} attribute.
If no dot is present, the entire \member{tp_name} field is made
accessible as the \member{__name__} attribute, and the
\member{__module__} attribute is undefined (unless explicitly set in
the dictionary, as explained above). This means your type will be
impossible to pickle.
This field is not inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{int}{tp_basicsize}
\cmemberline{PyTypeObject}{int}{tp_itemsize}
These fields allow calculating the size in bytes of instances of
the type.
There are two kinds of types: types with fixed-length instances have
a zero \member{tp_itemsize} field, types with variable-length
instances have a non-zero \member{tp_itemsize} field. For a type
with fixed-length instances, all instances have the same size,
given in \member{tp_basicsize}.
For a type with variable-length instances, the instances must have
an \member{ob_size} field, and the instance size is
\member{tp_basicsize} plus N times \member{tp_itemsize}, where N is
the ``length'' of the object. The value of N is typically stored in
the instance's \member{ob_size} field. There are exceptions: for
example, long ints use a negative \member{ob_size} to indicate a
negative number, and N is \code{abs(\member{ob_size})} there. Also,
the presence of an \member{ob_size} field in the instance layout
doesn't mean that the instance structure is variable-length (for
example, the structure for the list type has fixed-length instances,
yet those instances have a meaningful \member{ob_size} field).
The basic size includes the fields in the instance declared by the
macro \csimplemacro{PyObject_HEAD} or
\csimplemacro{PyObject_VAR_HEAD} (whichever is used to declare the
instance struct) and this in turn includes the \member{_ob_prev} and
\member{_ob_next} fields if they are present. This means that the
only correct way to get an initializer for the \member{tp_basicsize}
is to use the \keyword{sizeof} operator on the struct used to
declare the instance layout. The basic size does not include the GC
header size (this is new in Python 2.2; in 2.1 and 2.0, the GC
header size was included in \member{tp_basicsize}).
These fields are inherited separately by subtypes. If the base type
has a non-zero \member{tp_itemsize}, it is generally not safe to set
\member{tp_itemsize} to a different non-zero value in a subtype
(though this depends on the implementation of the base type).
A note about alignment: if the variable items require a particular
alignment, this should be taken care of by the value of
\member{tp_basicsize}. Example: suppose a type implements an array
of \code{double}. \member{tp_itemsize} is \code{sizeof(double)}.
It is the programmer's responsibility that \member{tp_basicsize} is
a multiple of \code{sizeof(double)} (assuming this is the alignment
requirement for \code{double}).
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{destructor}{tp_dealloc}
A pointer to the instance destructor function. This function must
be defined unless the type guarantees that its instances will never
be deallocated (as is the case for the singletons \code{None} and
\code{Ellipsis}).
The destructor function is called by the \cfunction{Py_DECREF()} and
\cfunction{Py_XDECREF()} macros when the new reference count is
zero. At this point, the instance is still in existence, but there
are no references to it. The destructor function should free all
references which the instance owns, free all memory buffers owned by
the instance (using the freeing function corresponding to the
allocation function used to allocate the buffer), and finally (as
its last action) call the type's \member{tp_free} function. If the
type is not subtypable (doesn't have the
\constant{Py_TPFLAGS_BASETYPE} flag bit set), it is permissible to
call the object deallocator directly instead of via
\member{tp_free}. The object deallocator should be the one used to
allocate the instance; this is normally \cfunction{PyObject_Del()}
if the instance was allocated using \cfunction{PyObject_New()} or
\cfunction{PyOject_VarNew()}, or \cfunction{PyObject_GC_Del()} if
the instance was allocated using \cfunction{PyObject_GC_New()} or
\cfunction{PyObject_GC_VarNew()}.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{printfunc}{tp_print}
An optional pointer to the instance print function.
The print function is only called when the instance is printed to a
\emph{real} file; when it is printed to a pseudo-file (like a
\class{StringIO} instance), the instance's \member{tp_repr} or
\member{tp_str} function is called to convert it to a string. These
are also called when the type's \member{tp_print} field is \NULL. A
type should never implement \member{tp_print} in a way that produces
different output than \member{tp_repr} or \member{tp_str} would.
The print function is called with the same signature as
\cfunction{PyObject_Print()}: \code{int tp_print(PyObject *self, FILE
*file, int flags)}. The \var{self} argument is the instance to be
printed. The \var{file} argument is the stdio file to which it is
to be printed. The \var{flags} argument is composed of flag bits.
The only flag bit currently defined is \constant{Py_PRINT_RAW}.
When the \constant{Py_PRINT_RAW} flag bit is set, the instance
should be printed the same way as \member{tp_str} would format it;
when the \constant{Py_PRINT_RAW} flag bit is clear, the instance
should be printed the same was as \member{tp_repr} would format it.
It should return \code{-1} and set an exception condition when an
error occurred during the comparison.
It is possible that the \member{tp_print} field will be deprecated.
In any case, it is recommended not to define \member{tp_print}, but
instead to rely on \member{tp_repr} and \member{tp_str} for
printing.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{getattrfunc}{tp_getattr}
An optional pointer to the get-attribute-string function.
This field is deprecated. When it is defined, it should point to a
function that acts the same as the \member{tp_getattro} function,
but taking a C string instead of a Python string object to give the
attribute name. The signature is the same as for
\cfunction{PyObject_GetAttrString()}.
This field is inherited by subtypes together with
\member{tp_getattro}: a subtype inherits both \member{tp_getattr}
and \member{tp_getattro} from its base type when the subtype's
\member{tp_getattr} and \member{tp_getattro} are both \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{setattrfunc}{tp_setattr}
An optional pointer to the set-attribute-string function.
This field is deprecated. When it is defined, it should point to a
function that acts the same as the \member{tp_setattro} function,
but taking a C string instead of a Python string object to give the
attribute name. The signature is the same as for
\cfunction{PyObject_SetAttrString()}.
This field is inherited by subtypes together with
\member{tp_setattro}: a subtype inherits both \member{tp_setattr}
and \member{tp_setattro} from its base type when the subtype's
\member{tp_setattr} and \member{tp_setattro} are both \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{cmpfunc}{tp_compare}
An optional pointer to the three-way comparison function.
The signature is the same as for \cfunction{PyObject_Compare()}.
The function should return \code{1} if \var{self} greater than
\var{other}, \code{0} if \var{self} is equal to \var{other}, and
\code{-1} if \var{self} less than \var{other}. It should return
\code{-1} and set an exception condition when an error occurred
during the comparison.
This field is inherited by subtypes together with
\member{tp_richcompare} and \member{tp_hash}: a subtypes inherits
all three of \member{tp_compare}, \member{tp_richcompare}, and
\member{tp_hash} when the subtype's \member{tp_compare},
\member{tp_richcompare}, and \member{tp_hash} are all \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{reprfunc}{tp_repr}
An optional pointer to a function that implements the built-in
function \function{repr()}.\bifuncindex{repr}
The signature is the same as for \cfunction{PyObject_Repr()}; it
must return a string or a Unicode object. Ideally, this function
should return a string that, when passed to \function{eval()}, given
a suitable environment, returns an object with the same value. If
this is not feasible, it should return a string starting with
\character{\textless} and ending with \character{\textgreater} from
which both the type and the value of the object can be deduced.
When this field is not set, a string of the form \samp{<\%s object
at \%p>} is returned, where \code{\%s} is replaced by the type name,
and \code{\%p} by the object's memory address.
This field is inherited by subtypes.
\end{cmemberdesc}
PyNumberMethods *tp_as_number;
XXX
PySequenceMethods *tp_as_sequence;
XXX
PyMappingMethods *tp_as_mapping;
XXX
\begin{cmemberdesc}{PyTypeObject}{hashfunc}{tp_hash}
An optional pointer to a function that implements the built-in
function \function{hash()}.\bifuncindex{hash}
The signature is the same as for \cfunction{PyObject_Hash()}; it
must return a C long. The value \code{-1} should not be returned as
a normal return value; when an error occurs during the computation
of the hash value, the function should set an exception and return
\code{-1}.
When this field is not set, two possibilities exist: if the
\member{tp_compare} and \member{tp_richcompare} fields are both
\NULL, a default hash value based on the object's address is
returned; otherwise, a \exception{TypeError} is raised.
This field is inherited by subtypes together with
\member{tp_richcompare} and \member{tp_compare}: a subtypes inherits
all three of \member{tp_compare}, \member{tp_richcompare}, and
\member{tp_hash}, when the subtype's \member{tp_compare},
\member{tp_richcompare} and \member{tp_hash} are all \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{ternaryfunc}{tp_call}
An optional pointer to a function that implements calling the
object. This should be \NULL{} if the object is not callable. The
signature is the same as for \cfunction{PyObject_Call()}.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{reprfunc}{tp_str}
An optional pointer to a function that implements the built-in
operation \function{str()}. (Note that \class{str} is a type now,
and \function{str()} calls the constructor for that type. This
constructor calls \cfunction{PyObject_Str()} to do the actual work,
and \cfunction{PyObject_Str()} will call this handler.)
The signature is the same as for \cfunction{PyObject_Str()}; it must
return a string or a Unicode object. This function should return a
``friendly'' string representation of the object, as this is the
representation that will be used by the print statement.
When this field is not set, \cfunction{PyObject_Repr()} is called to
return a string representation.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{getattrofunc}{tp_getattro}
An optional pointer to the get-attribute function.
The signature is the same as for \cfunction{PyObject_GetAttr()}. It
is usually convenient to set this field to
\cfunction{PyObject_GenericGetAttr()}, which implements the normal
way of looking for object attributes.
This field is inherited by subtypes together with
\member{tp_getattr}: a subtype inherits both \member{tp_getattr} and
\member{tp_getattro} from its base type when the subtype's
\member{tp_getattr} and \member{tp_getattro} are both \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{setattrofunc}{tp_setattro}
An optional pointer to the set-attribute function.
The signature is the same as for \cfunction{PyObject_SetAttr()}. It
is usually convenient to set this field to
\cfunction{PyObject_GenericSetAttr()}, which implements the normal
way of setting object attributes.
This field is inherited by subtypes together with
\member{tp_setattr}: a subtype inherits both \member{tp_setattr} and
\member{tp_setattro} from its base type when the subtype's
\member{tp_setattr} and \member{tp_setattro} are both \NULL.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyBufferProcs*}{tp_as_buffer}
Pointer to an additional structure that contains fields relevant only to
objects which implement the buffer interface. These fields are
documented in ``Buffer Object Structures'' (section
\ref{buffer-structs}).
The \member{tp_as_buffer} field is not inherited, but the contained
fields are inherited individually.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{long}{tp_flags}
This field is a bit mask of various flags. Some flags indicate
variant semantics for certain situations; others are used to
indicate that certain fields in the type object (or in the extension
structures referenced via \member{tp_as_number},
\member{tp_as_sequence}, \member{tp_as_mapping}, and
\member{tp_as_buffer}) that were historically not always present are
valid; if such a flag bit is clear, the type fields it guards must
not be accessed and must be considered to have a zero or \NULL{}
value instead.
Inheritance of this field is complicated. Most flag bits are
inherited individually, i.e. if the base type has a flag bit set,
the subtype inherits this flag bit. The flag bits that pertain to
extension structures are strictly inherited if the extension
structure is inherited, i.e. the base type's value of the flag bit
is copied into the subtype together with a pointer to the extension
structure. The \constant{Py_TPFLAGS_HAVE_GC} flag bit is inherited
together with the \member{tp_traverse} and \member{tp_clear} fields,
i.e. if the \constant{Py_TPFLAGS_HAVE_GC} flag bit is clear in the
subtype and the \member{tp_traverse} and \member{tp_clear} fields in
the subtype exist (as indicated by the
\constant{Py_TPFLAGS_HAVE_RICHCOMPARE} flag bit) and have \NULL{}
values.
The following bit masks are currently defined; these can be or-ed
together using the \code{|} operator to form the value of the
\member{tp_flags} field. The macro \cfunction{PyType_HasFeature()}
takes a type and a flags value, \var{tp} and \var{f}, and checks
whether \code{\var{tp}->tp_flags \& \var{f}} is non-zero.
\begin{datadesc}{Py_TPFLAGS_HAVE_GETCHARBUFFER}
If this bit is set, the \ctype{PyBufferProcs} struct referenced by
\member{tp_as_buffer} has the \member{bf_getcharbuffer} field.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_SEQUENCE_IN}
If this bit is set, the \ctype{PySequenceMethods} struct
referenced by \member{tp_as_sequence} has the \member{sq_contains}
field.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_GC}
This bit is obsolete. The bit it used to name is no longer in
use. The symbol is now defined as zero.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_INPLACEOPS}
If this bit is set, the \ctype{PySequenceMethods} struct
referenced by \member{tp_as_sequence} and the
\ctype{PyNumberMethods} structure referenced by
\member{tp_as_number} contain the fields for in-place operators.
In particular, this means that the \ctype{PyNumberMethods}
structure has the fields \member{nb_inplace_add},
\member{nb_inplace_subtract}, \member{nb_inplace_multiply},
\member{nb_inplace_divide}, \member{nb_inplace_remainder},
\member{nb_inplace_power}, \member{nb_inplace_lshift},
\member{nb_inplace_rshift}, \member{nb_inplace_and},
\member{nb_inplace_xor}, and \member{nb_inplace_or}; and the
\ctype{PySequenceMethods} struct has the fields
\member{sq_inplace_concat} and \member{sq_inplace_repeat}.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_CHECKTYPES}
If this bit is set, the binary and ternary operations in the
\ctype{PyNumberMethods} structure referenced by
\member{tp_as_number} accept arguments of arbitrary object types,
and do their own type conversions if needed. If this bit is
clear, those operations require that all arguments have the
current type as their type, and the caller is supposed to perform
a coercion operation first. This applies to \member{nb_add},
\member{nb_subtract}, \member{nb_multiply}, \member{nb_divide},
\member{nb_remainder}, \member{nb_divmod}, \member{nb_power},
\member{nb_lshift}, \member{nb_rshift}, \member{nb_and},
\member{nb_xor}, and \member{nb_or}.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_RICHCOMPARE}
If this bit is set, the type object has the
\member{tp_richcompare} field, as well as the \member{tp_traverse}
and the \member{tp_clear} fields.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_WEAKREFS}
If this bit is set, the \member{tp_weaklistoffset} field is
defined. Instances of a type are weakly referenceable if the
type's \member{tp_weaklistoffset} field has a value greater than
zero.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_ITER}
If this bit is set, the type object has the \member{tp_iter} and
\member{tp_iternext} fields.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_CLASS}
If this bit is set, the type object has several new fields defined
starting in Python 2.2: \member{tp_methods}, \member{tp_members},
\member{tp_getset}, \member{tp_base}, \member{tp_dict},
\member{tp_descr_get}, \member{tp_descr_set},
\member{tp_dictoffset}, \member{tp_init}, \member{tp_alloc},
\member{tp_new}, \member{tp_free}, \member{tp_is_gc},
\member{tp_bases}, \member{tp_mro}, \member{tp_cache},
\member{tp_subclasses}, and \member{tp_weaklist}.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HEAPTYPE}
This bit is set when the type object itself is allocated on the
heap. In this case, the \member{ob_type} field of its instances
is considered a reference to the type, and the type object is
INCREF'ed when a new instance is created, and DECREF'ed when an
instance is destroyed (this does not apply to instances of
subtypes; only the type referenced by the instance's ob_type gets
INCREF'ed or DECREF'ed).
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_BASETYPE}
This bit is set when the type can be used as the base type of
another type. If this bit is clear, the type cannot be subtyped
(similar to a "final" class in Java).
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_READY}
This bit is set when the type object has been fully initialized by
\cfunction{PyType_Ready()}.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_READYING}
This bit is set while \cfunction{PyType_Ready()} is in the process
of initializing the type object.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_GC}
This bit is set when the object supports garbage collection. If
this bit is set, instances must be created using
\cfunction{PyObject_GC_New()} and destroyed using
\cfunction{PyObject_GC_Del()}. More information in section XXX
about garbage collection. This bit also implies that the
GC-related fields \member{tp_traverse} and \member{tp_clear} are
present in the type object; but those fields also exist when
\constant{Py_TPFLAGS_HAVE_GC} is clear but
\constant{Py_TPFLAGS_HAVE_RICHCOMPARE} is set.
\end{datadesc}
\begin{datadesc}{Py_TPFLAGS_DEFAULT}
This is a bitmask of all the bits that pertain to the existence of
certain fields in the type object and its extension structures.
Currently, it includes the following bits:
\constant{Py_TPFLAGS_HAVE_GETCHARBUFFER},
\constant{Py_TPFLAGS_HAVE_SEQUENCE_IN},
\constant{Py_TPFLAGS_HAVE_INPLACEOPS},
\constant{Py_TPFLAGS_HAVE_RICHCOMPARE},
\constant{Py_TPFLAGS_HAVE_WEAKREFS},
\constant{Py_TPFLAGS_HAVE_ITER}, and
\constant{Py_TPFLAGS_HAVE_CLASS}.
\end{datadesc}
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{char*}{tp_doc}
An optional pointer to a NUL-terminated C string giving the
docstring for this type object. This is exposed as the
\member{__doc__} attribute on the type and instances of the type.
This field is \emph{not} inherited by subtypes.
\end{cmemberdesc}
The following three fields only exist if the
\constant{Py_TPFLAGS_HAVE_RICHCOMPARE} flag bit is set.
\begin{cmemberdesc}{PyTypeObject}{traverseproc}{tp_traverse}
An optional pointer to a traversal function for the garbage
collector. This is only used if the \constant{Py_TPFLAGS_HAVE_GC}
flag bit is set. More information in section
\ref{supporting-cycle-detection} about garbage collection.
This field is inherited by subtypes together with \member{tp_clear}
and the \constant{Py_TPFLAGS_HAVE_GC} flag bit: the flag bit,
\member{tp_traverse}, and \member{tp_clear} are all inherited from
the base type if they are all zero in the subtype \emph{and} the
subtype has the \constant{Py_TPFLAGS_HAVE_RICHCOMPARE} flag bit set.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{inquiry}{tp_clear}
An optional pointer to a clear function for the garbage collector.
This is only used if the \constant{Py_TPFLAGS_HAVE_GC} flag bit is
set. More information in section
\ref{supporting-cycle-detection} about garbage collection.
This field is inherited by subtypes together with \member{tp_clear}
and the \constant{Py_TPFLAGS_HAVE_GC} flag bit: the flag bit,
\member{tp_traverse}, and \member{tp_clear} are all inherited from
the base type if they are all zero in the subtype \emph{and} the
subtype has the \constant{Py_TPFLAGS_HAVE_RICHCOMPARE} flag bit set.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{richcmpfunc}{tp_richcompare}
An optional pointer to the rich comparison function.
The signature is the same as for \cfunction{PyObject_RichCompare()}.
The function should return \code{1} if the requested comparison
returns true, \code{0} if it returns false. It should return
\code{-1} and set an exception condition when an error occurred
during the comparison.
This field is inherited by subtypes together with
\member{tp_compare} and \member{tp_hash}: a subtype inherits all
three of \member{tp_compare}, \member{tp_richcompare}, and
\member{tp_hash}, when the subtype's \member{tp_compare},
\member{tp_richcompare}, and \member{tp_hash} are all \NULL.
The following constants are defined to be used as the third argument
for \member{tp_richcompare} and for \cfunction{PyObject_RichCompare()}:
\begin{tableii}{l|c}{constant}{Constant}{Comparison}
\lineii{Py_LT}{\code{<}}
\lineii{Py_LE}{\code{<=}}
\lineii{Py_EQ}{\code{==}}
\lineii{Py_NE}{\code{!=}}
\lineii{Py_GT}{\code{>}}
\lineii{Py_GE}{\code{>=}}
\end{tableii}
\end{cmemberdesc}
The next field only exists if the \constant{Py_TPFLAGS_HAVE_WEAKREFS}
flag bit is set.
\begin{cmemberdesc}{PyTypeObject}{long}{tp_weaklistoffset}
If the instances of this type are weakly referenceable, this field
is greater than zero and contains the offset in the instance
structure of the weak reference list head (ignoring the GC header,
if present); this offset is used by
\cfunction{PyObject_ClearWeakRefs()} and the
\cfunction{PyWeakref_*()} functions. The instance structure needs
to include a field of type \ctype{PyObject*} which is initialized to
\NULL.
Do not confuse this field with \member{tp_weaklist}; that is the
list head for weak references to the type object itself.
This field is inherited by subtypes, but see the rules listed below.
A subtype may override this offset; this means that the subtype uses
a different weak reference list head than the base type. Since the
list head is always found via \member{tp_weaklistoffset}, this
should not be a problem.
When a type defined by a class statement has no \member{__slots__}
declaration, and none of its base types are weakly referenceable,
the type is made weakly referenceable by adding a weak reference
list head slot to the instance layout and setting the
\member{tp_weaklistoffset} of that slot's offset.
When a type's \member{__slots__} declaration contains a slot named
\member{__weakref__}, that slot becomes the weak reference list head
for instances of the type, and the slot's offset is stored in the
type's \member{tp_weaklistoffset}.
When a type's \member{__slots__} declaration does not contain a slot
named \member{__weakref__}, the type inherits its
\member{tp_weaklistoffset} from its base type.
\end{cmemberdesc}
The next two fields only exist if the
\constant{Py_TPFLAGS_HAVE_CLASS} flag bit is set.
\begin{cmemberdesc}{PyTypeObject}{getiterfunc}{tp_iter}
An optional pointer to a function that returns an iterator for the
object. Its presence normally signals that the instances of this
type are iterable (although sequences may be iterable without this
function, and classic instances always have this function, even if
they don't define an \method{__iter__()} method).
This function has the same signature as
\cfunction{PyObject_GetIter()}.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{iternextfunc}{tp_iternext}
An optional pointer to a function that returns the next item in an
iterator, or raises \exception{StopIteration} when the iterator is
exhausted. Its presence normally signals that the instances of this
type are iterators (although classic instances always have this
function, even if they don't define a \method{next()} method).
Iterator types should also define the \member{tp_iter} function, and
that function should return the iterator instance itself (not a new
iterator instance).
This function has the same signature as \cfunction{PyIter_Next()}.
This field is inherited by subtypes.
\end{cmemberdesc}
The next fields, up to and including \member{tp_weaklist}, only exist
if the \constant{Py_TPFLAGS_HAVE_CLASS} flag bit is set.
\begin{cmemberdesc}{PyTypeObject}{struct PyMethodDef*}{tp_methods}
An optional pointer to a static \NULL-terminated array of
\ctype{PyMethodDef} structures, declaring regular methods of this
type.
For each entry in the array, an entry is added to the type's
dictionary (see \member{tp_dict} below) containing a method
descriptor.
This field is not inherited by subtypes (methods are
inherited through a different mechanism).
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{struct PyMemberDef*}{tp_members}
An optional pointer to a static \NULL-terminated array of
\ctype{PyMemberDef} structures, declaring regular data members
(fields or slots) of instances of this type.
For each entry in the array, an entry is added to the type's
dictionary (see \member{tp_dict} below) containing a member
descriptor.
This field is not inherited by subtypes (members are inherited
through a different mechanism).
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{struct PyGetSetDef*}{tp_getset}
An optional pointer to a static \NULL-terminated array of
\ctype{PyGetSetDef} structures, declaring computed attributes of
instances of this type.
For each entry in the array, an entry is added to the type's
dictionary (see \member{tp_dict} below) containing a getset
descriptor.
This field is not inherited by subtypes (computed attributes are
inherited through a different mechanism).
Docs for PyGetSetDef (XXX belong elsewhere):
\begin{verbatim}
typedef PyObject *(*getter)(PyObject *, void *);
typedef int (*setter)(PyObject *, PyObject *, void *);
typedef struct PyGetSetDef {
char *name; /* attribute name */
getter get; /* C function to get the attribute */
setter set; /* C function to set the attribute */
char *doc; /* optional doc string */
void *closure; /* optional additional data for getter and setter */
} PyGetSetDef;
\end{verbatim}
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyTypeObject*}{tp_base}
An optional pointer to a base type from which type properties are
inherited. At this level, only single inheritance is supported;
multiple inheritance require dynamically creating a type object by
calling the metatype.
This field is not inherited by subtypes (obviously), but it defaults
to \code{\&PyBaseObject_Type} (which to Python programmers is known
as the type \class{object}).
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_dict}
The type's dictionary is stored here by \cfunction{PyType_Ready()}.
This field should normally be initialized to \NULL{} before
PyType_Ready is called; it may also be initialized to a dictionary
containing initial attributes for the type. Once
\cfunction{PyType_Ready()} has initialized the type, extra
attributes for the type may be added to this dictionary only if they
don't correspond to overloaded operations (like \method{__add__()}).
This field is not inherited by subtypes (though the attributes
defined in here are inherited through a different mechanism).
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{descrgetfunc}{tp_descr_get}
An optional pointer to a "descriptor get" function.
XXX blah, blah.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{descrsetfunc}{tp_descr_set}
An optional pointer to a "descriptor set" function.
XXX blah, blah.
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{long}{tp_dictoffset}
If the instances of this type have a dictionary containing instance
variables, this field is non-zero and contains the offset in the
instances of the type of the instance variable dictionary; this
offset is used by \cfunction{PyObject_GenericGetAttr()}.
Do not confuse this field with \member{tp_dict}; that is the
dictionary for attributes of the type object itself.
If the value of this field is greater than zero, it specifies the
offset from the start of the instance structure. If the value is
less than zero, it specifies the offset from the \emph{end} of the
instance structure. A negative offset is more expensive to use, and
should only be used when the instance structure contains a
variable-length part. This is used for example to add an instance
variable dictionary to subtypes of \class{str} or \class{tuple}.
Note that the \member{tp_basicsize} field should account for the
dictionary added to the end in that case, even though the dictionary
is not included in the basic object layout. On a system with a
pointer size of 4 bytes, \member{tp_dictoffset} should be set to
\code{-4} to indicate that the dictionary is at the very end of the
structure.
The real dictionary offset in an instance can be computed from a
negative \member{tp_dictoffset} as follows:
\begin{verbatim}
dictoffset = tp_basicsize + abs(ob_size)*tp_itemsize + tp_dictoffset
if dictoffset is not aligned on sizeof(void*):
round up to sizeof(void*)
\end{verbatim}
where \member{tp_basicsize}, \member{tp_itemsize} and
\member{tp_dictoffset} are taken from the type object, and
\member{ob_size} is taken from the instance. The absolute value is
taken because long ints use the sign of \member{ob_size} to store
the sign of the number. (There's never a need to do this
calculation yourself; it is done for you by
\cfunction{_PyObject_GetDictPtr()}.)
This field is inherited by subtypes, but see the rules listed below.
A subtype may override this offset; this means that the subtype
instances store the dictionary at a difference offset than the base
type. Since the dictionary is always found via
\member{tp_dictoffset}, this should not be a problem.
When a type defined by a class statement has no \member{__slots__}
declaration, and none of its base types has an instance variable
dictionary, a dictionary slot is added to the instance layout and
the \member{tp_dictoffset} is set to that slot's offset.
When a type defined by a class statement has a \member{__slots__}
declaration, the type inherits its \member{tp_dictoffset} from its
base type.
(Adding a slot named \member{__dict__} to the \member{__slots__}
declaration does not have the expected effect, it just causes
confusion. Maybe this should be added as a feature just like
\member{__weakref__} though.)
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{initproc}{tp_init}
An optional pointer to an instance initialization function.
This function corresponds to the \method{__init__()} method of
classes. Like \method{__init__()}, it is possible to create an
instance without calling \method{__init__()}, and it is possible to
reinitialize an instance by calling its \method{__init__()} method
again.
The function signature is
\begin{verbatim}
int tp_init(PyObject *self, PyObject *args, PyObject *kwds)
\end{verbatim}
The self argument is the instance to be initialized; the \var{args}
and \var{kwds} arguments represent positional and keyword arguments
of the call to \method{__init__()}.
The \member{tp_init} function, if not \NULL, is called when an
instance is created normally by calling its type, after the type's
\member{tp_new} function has returned an instance of the type. If
the \member{tp_new} function returns an instance of some other type
that is not a subtype of the original type, no \member{tp_init}
function is called; if \member{tp_new} returns an instance of a
subtype of the original type, the subtype's \member{tp_init} is
called. (VERSION NOTE: described here is what is implemented in
Python 2.2.1 and later. In Python 2.2, the \member{tp_init} of the
type of the object returned by \member{tp_new} was always called, if
not \NULL.)
This field is inherited by subtypes.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{allocfunc}{tp_alloc}
An optional pointer to an instance allocation function.
The function signature is
\begin{verbatim}
PyObject *tp_alloc(PyTypeObject *self, int nitems)
\end{verbatim}
The purpose of this function is to separate memory allocation from
memory initialization. It should return a pointer to a block of
memory of adequate length for the instance, suitably aligned, and
initialized to zeros, but with \member{ob_refcnt} set to \code{1}
and \member{ob_type} set to the type argument. If the type's
\member{tp_itemsize} is non-zero, the object's \member{ob_size} field
should be initialized to \var{nitems} and the length of the
allocated memory block should be \code{tp_basicsize +
\var{nitems}*tp_itemsize}, rounded up to a multiple of
\code{sizeof(void*)}; otherwise, \var{nitems} is not used and the
length of the block should be \member{tp_basicsize}.
Do not use this function to do any other instance initialization,
not even to allocate additional memory; that should be done by
\member{tp_new}.
This field is inherited by static subtypes, but not by dynamic
subtypes (subtypes created by a class statement); in the latter,
this field is always set to \cfunction{PyType_GenericAlloc()}, to
force a standard heap allocation strategy. That is also the
recommended value for statically defined types.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{newfunc}{tp_new}
An optional pointer to an instance creation function.
If this function is \NULL{} for a particular type, that type cannot
be called to create new instances; presumably there is some other
way to create instances, like a factory function.
The function signature is
\begin{verbatim}
PyObject *tp_new(PyTypeObject *subtype, PyObject *args, PyObject *kwds)
\end{verbatim}
The subtype argument is the type of the object being created; the
\var{args} and \var{kwds} arguments represent positional and keyword
arguments of the call to the type. Note that subtype doesn't have
to equal the type whose \member{tp_new} function is called; it may
be a subtype of that type (but not an unrelated type).
The \member{tp_new} function should call
\code{\var{subtype}->tp_alloc(\var{subtype}, \var{nitems})} to
allocate space for the object, and then do only as much further
initialization as is absolutely necessary. Initialization that can
safely be ignored or repeated should be placed in the
\member{tp_init} handler. A good rule of thumb is that for
immutable types, all initialization should take place in
\member{tp_new}, while for mutable types, most initialization should
be deferred to \member{tp_init}.
This field is inherited by subtypes, except it is not inherited by
static types whose \member{tp_base} is \NULL{} or
\code{\&PyBaseObject_Type}. The latter exception is a precaution so
that old extension types don't become callable simply by being
linked with Python 2.2.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{destructor}{tp_free}
An optional pointer to an instance deallocation function.
The signature of this function has changed slightly: in Python
2.2 and 2.2.1, its signature is \ctype{destructor}:
\begin{verbatim}
void tp_free(PyObject *)
\end{verbatim}
In Python 2.3 and beyond, its signature is \ctype{freefunc}:
\begin{verbatim}
void tp_free(void *)
\end{verbatim}
The only initializer that is compatible with both versions is
\code{_PyObject_Del}, whose definition has suitably adapted in
Python 2.3.
This field is inherited by static subtypes, but not by dynamic
subtypes (subtypes created by a class statement); in the latter,
this field is set to a deallocator suitable to match
\cfunction{PyType_GenericAlloc()} and the value of the
\constant{Py_TPFLAGS_HAVE_GC} flag bit.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{inquiry}{tp_is_gc}
An optional pointer to a function called by the garbage collector.
The garbage collector needs to know whether a particular object is
collectible or not. Normally, it is sufficient to look at the
object's type's \member{tp_flags} field, and check the
\constant{Py_TPFLAGS_HAVE_GC} flag bit. But some types have a
mixture of statically and dynamically allocated instances, and the
statically allocated instances are not collectible. Such types
should define this function; it should return \code{1} for a
collectible instance, and \code{0} for a non-collectible instance.
The signature is
\begin{verbatim}
int tp_is_gc(PyObject *self)
\end{verbatim}
(The only example of this are types themselves. The metatype,
\cdata{PyType_Type}, defines this function to distinguish between
statically and dynamically allocated types.)
This field is inherited by subtypes. (VERSION NOTE: in Python
2.2, it was not inherited. It is inherited in 2.2.1 and later
versions.)
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_bases}
Tuple of base types.
This is set for types created by a class statement. It should be
\NULL{} for statically defined types.
This field is not inherited.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_mro}
Tuple containing the expanded set of base types, starting with the
type itself and ending with \class{object}, in Method Resolution
Order.
This field is not inherited; it is calculated fresh by
\cfunction{PyType_Ready()}.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_cache}
Unused. Not inherited. Internal use only.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_subclasses}
List of weak references to subclasses. Not inherited. Internal
use only.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyObject*}{tp_weaklist}
Weak reference list head, for weak references to this type
object. Not inherited. Internal use only.
\end{cmemberdesc}
The remaining fields are only defined if the feature test macro
\constant{COUNT_ALLOCS} is defined, and are for internal use only.
They are documented here for completeness. None of these fields are
inherited by subtypes.
\begin{cmemberdesc}{PyTypeObject}{int}{tp_allocs}
Number of allocations.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{int}{tp_frees}
Number of frees.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{int}{tp_maxalloc}
Maximum simultaneously allocated objects.
\end{cmemberdesc}
\begin{cmemberdesc}{PyTypeObject}{PyTypeObject*}{tp_next}
Pointer to the next type object with a non-zero \member{tp_allocs}
field.
\end{cmemberdesc}
Also, note that, in a garbage collected Python, tp_dealloc may be
called from any Python thread, not just the thread which created the
object (if the object becomes part of a refcount cycle, that cycle
might be collected by a garbage collection on any thread). This is
not a problem for Python API calls, since the thread on which
tp_dealloc is called will own the Global Interpreter Lock (GIL).
However, if the object being destroyed in turn destroys objects from
some other C or \Cpp{} library, care should be taken to ensure that
destroying those objects on the thread which called tp_dealloc will
not violate any assumptions of the library.
\section{Mapping Object Structures \label{mapping-structs}}
\begin{ctypedesc}{PyMappingMethods}
Structure used to hold pointers to the functions used to implement
the mapping protocol for an extension type.
\end{ctypedesc}
\section{Number Object Structures \label{number-structs}}
\begin{ctypedesc}{PyNumberMethods}
Structure used to hold pointers to the functions an extension type
uses to implement the number protocol.
\end{ctypedesc}
\section{Sequence Object Structures \label{sequence-structs}}
\begin{ctypedesc}{PySequenceMethods}
Structure used to hold pointers to the functions which an object
uses to implement the sequence protocol.
\end{ctypedesc}
\section{Buffer Object Structures \label{buffer-structs}}
\sectionauthor{Greg J. Stein}{greg@lyra.org}
The buffer interface exports a model where an object can expose its
internal data as a set of chunks of data, where each chunk is
specified as a pointer/length pair. These chunks are called
\dfn{segments} and are presumed to be non-contiguous in memory.
If an object does not export the buffer interface, then its
\member{tp_as_buffer} member in the \ctype{PyTypeObject} structure
should be \NULL. Otherwise, the \member{tp_as_buffer} will point to
a \ctype{PyBufferProcs} structure.
\note{It is very important that your \ctype{PyTypeObject} structure
uses \constant{Py_TPFLAGS_DEFAULT} for the value of the
\member{tp_flags} member rather than \code{0}. This tells the Python
runtime that your \ctype{PyBufferProcs} structure contains the
\member{bf_getcharbuffer} slot. Older versions of Python did not have
this member, so a new Python interpreter using an old extension needs
to be able to test for its presence before using it.}
\begin{ctypedesc}{PyBufferProcs}
Structure used to hold the function pointers which define an
implementation of the buffer protocol.
The first slot is \member{bf_getreadbuffer}, of type
\ctype{getreadbufferproc}. If this slot is \NULL, then the object
does not support reading from the internal data. This is
non-sensical, so implementors should fill this in, but callers
should test that the slot contains a non-\NULL{} value.
The next slot is \member{bf_getwritebuffer} having type
\ctype{getwritebufferproc}. This slot may be \NULL{} if the object
does not allow writing into its returned buffers.
The third slot is \member{bf_getsegcount}, with type
\ctype{getsegcountproc}. This slot must not be \NULL{} and is used
to inform the caller how many segments the object contains. Simple
objects such as \ctype{PyString_Type} and \ctype{PyBuffer_Type}
objects contain a single segment.
The last slot is \member{bf_getcharbuffer}, of type
\ctype{getcharbufferproc}. This slot will only be present if the
\constant{Py_TPFLAGS_HAVE_GETCHARBUFFER} flag is present in the
\member{tp_flags} field of the object's \ctype{PyTypeObject}.
Before using this slot, the caller should test whether it is present
by using the
\cfunction{PyType_HasFeature()}\ttindex{PyType_HasFeature()}
function. If present, it may be \NULL, indicating that the object's
contents cannot be used as \emph{8-bit characters}.
The slot function may also raise an error if the object's contents
cannot be interpreted as 8-bit characters. For example, if the
object is an array which is configured to hold floating point
values, an exception may be raised if a caller attempts to use
\member{bf_getcharbuffer} to fetch a sequence of 8-bit characters.
This notion of exporting the internal buffers as ``text'' is used to
distinguish between objects that are binary in nature, and those
which have character-based content.
\note{The current policy seems to state that these characters
may be multi-byte characters. This implies that a buffer size of
\var{N} does not mean there are \var{N} characters present.}
\end{ctypedesc}
\begin{datadesc}{Py_TPFLAGS_HAVE_GETCHARBUFFER}
Flag bit set in the type structure to indicate that the
\member{bf_getcharbuffer} slot is known. This being set does not
indicate that the object supports the buffer interface or that the
\member{bf_getcharbuffer} slot is non-\NULL.
\end{datadesc}
\begin{ctypedesc}[getreadbufferproc]{int (*getreadbufferproc)
(PyObject *self, int segment, void **ptrptr)}
Return a pointer to a readable segment of the buffer. This function
is allowed to raise an exception, in which case it must return
\code{-1}. The \var{segment} which is passed must be zero or
positive, and strictly less than the number of segments returned by
the \member{bf_getsegcount} slot function. On success, it returns
the length of the buffer memory, and sets \code{*\var{ptrptr}} to a
pointer to that memory.
\end{ctypedesc}
\begin{ctypedesc}[getwritebufferproc]{int (*getwritebufferproc)
(PyObject *self, int segment, void **ptrptr)}
Return a pointer to a writable memory buffer in
\code{*\var{ptrptr}}, and the length of that segment as the function
return value. The memory buffer must correspond to buffer segment
\var{segment}. Must return \code{-1} and set an exception on
error. \exception{TypeError} should be raised if the object only
supports read-only buffers, and \exception{SystemError} should be
raised when \var{segment} specifies a segment that doesn't exist.
% Why doesn't it raise ValueError for this one?
% GJS: because you shouldn't be calling it with an invalid
% segment. That indicates a blatant programming error in the C
% code.
\end{ctypedesc}
\begin{ctypedesc}[getsegcountproc]{int (*getsegcountproc)
(PyObject *self, int *lenp)}
Return the number of memory segments which comprise the buffer. If
\var{lenp} is not \NULL, the implementation must report the sum of
the sizes (in bytes) of all segments in \code{*\var{lenp}}.
The function cannot fail.
\end{ctypedesc}
\begin{ctypedesc}[getcharbufferproc]{int (*getcharbufferproc)
(PyObject *self, int segment, const char **ptrptr)}
Return the size of the memory buffer in \var{ptrptr} for segment
\var{segment}. \code{*\var{ptrptr}} is set to the memory buffer.
\end{ctypedesc}
\section{Supporting the Iterator Protocol
\label{supporting-iteration}}
\section{Supporting Cyclic Garbage Collection
\label{supporting-cycle-detection}}
Python's support for detecting and collecting garbage which involves
circular references requires support from object types which are
``containers'' for other objects which may also be containers. Types
which do not store references to other objects, or which only store
references to atomic types (such as numbers or strings), do not need
to provide any explicit support for garbage collection.
An example showing the use of these interfaces can be found in
``\ulink{Supporting the Cycle
Collector}{../ext/example-cycle-support.html}'' in
\citetitle[../ext/ext.html]{Extending and Embedding the Python
Interpreter}.
To create a container type, the \member{tp_flags} field of the type
object must include the \constant{Py_TPFLAGS_HAVE_GC} and provide an
implementation of the \member{tp_traverse} handler. If instances of the
type are mutable, a \member{tp_clear} implementation must also be
provided.
\begin{datadesc}{Py_TPFLAGS_HAVE_GC}
Objects with a type with this flag set must conform with the rules
documented here. For convenience these objects will be referred to
as container objects.
\end{datadesc}
Constructors for container types must conform to two rules:
\begin{enumerate}
\item The memory for the object must be allocated using
\cfunction{PyObject_GC_New()} or \cfunction{PyObject_GC_VarNew()}.
\item Once all the fields which may contain references to other
containers are initialized, it must call
\cfunction{PyObject_GC_Track()}.
\end{enumerate}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_GC_New}{TYPE, PyTypeObject *type}
Analogous to \cfunction{PyObject_New()} but for container objects with
the \constant{Py_TPFLAGS_HAVE_GC} flag set.
\end{cfuncdesc}
\begin{cfuncdesc}{\var{TYPE}*}{PyObject_GC_NewVar}{TYPE, PyTypeObject *type,
int size}
Analogous to \cfunction{PyObject_NewVar()} but for container objects
with the \constant{Py_TPFLAGS_HAVE_GC} flag set.
\end{cfuncdesc}
\begin{cfuncdesc}{PyVarObject *}{PyObject_GC_Resize}{PyVarObject *op, int}
Resize an object allocated by \cfunction{PyObject_NewVar()}. Returns
the resized object or \NULL{} on failure.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{PyObject_GC_Track}{PyObject *op}
Adds the object \var{op} to the set of container objects tracked by
the collector. The collector can run at unexpected times so objects
must be valid while being tracked. This should be called once all
the fields followed by the \member{tp_traverse} handler become valid,
usually near the end of the constructor.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{_PyObject_GC_TRACK}{PyObject *op}
A macro version of \cfunction{PyObject_GC_Track()}. It should not be
used for extension modules.
\end{cfuncdesc}
Similarly, the deallocator for the object must conform to a similar
pair of rules:
\begin{enumerate}
\item Before fields which refer to other containers are invalidated,
\cfunction{PyObject_GC_UnTrack()} must be called.
\item The object's memory must be deallocated using
\cfunction{PyObject_GC_Del()}.
\end{enumerate}
\begin{cfuncdesc}{void}{PyObject_GC_Del}{PyObject *op}
Releases memory allocated to an object using
\cfunction{PyObject_GC_New()} or \cfunction{PyObject_GC_NewVar()}.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{PyObject_GC_UnTrack}{PyObject *op}
Remove the object \var{op} from the set of container objects tracked
by the collector. Note that \cfunction{PyObject_GC_Track()} can be
called again on this object to add it back to the set of tracked
objects. The deallocator (\member{tp_dealloc} handler) should call
this for the object before any of the fields used by the
\member{tp_traverse} handler become invalid.
\end{cfuncdesc}
\begin{cfuncdesc}{void}{_PyObject_GC_UNTRACK}{PyObject *op}
A macro version of \cfunction{PyObject_GC_UnTrack()}. It should not be
used for extension modules.
\end{cfuncdesc}
The \member{tp_traverse} handler accepts a function parameter of this
type:
\begin{ctypedesc}[visitproc]{int (*visitproc)(PyObject *object, void *arg)}
Type of the visitor function passed to the \member{tp_traverse}
handler. The function should be called with an object to traverse
as \var{object} and the third parameter to the \member{tp_traverse}
handler as \var{arg}. The Python core uses several visitor functions
to implement cyclic garbage detection; it's not expected that users will
need to write their own visitor functions.
\end{ctypedesc}
The \member{tp_traverse} handler must have the following type:
\begin{ctypedesc}[traverseproc]{int (*traverseproc)(PyObject *self,
visitproc visit, void *arg)}
Traversal function for a container object. Implementations must
call the \var{visit} function for each object directly contained by
\var{self}, with the parameters to \var{visit} being the contained
object and the \var{arg} value passed to the handler. The \var{visit}
function must not be called with a \NULL{} object argument. If
\var{visit} returns a non-zero value
that value should be returned immediately.
\end{ctypedesc}
To simplify writing \member{tp_traverse} handlers, a
\cfunction{Py_VISIT()} macro is provided. In order to use this macro,
the \member{tp_traverse} implementation must name its arguments
exactly \var{visit} and \var{arg}:
\begin{cfuncdesc}{void}{Py_VISIT}{PyObject *o}
Call the \var{visit} callback, with arguments \var{o} and \var{arg}.
If \var{visit} returns a non-zero value, then return it. Using this
macro, \member{tp_traverse} handlers look like:
\begin{verbatim}
static int
my_traverse(Noddy *self, visitproc visit, void *arg)
{
Py_VISIT(self->foo);
Py_VISIT(self->bar);
return 0;
}
\end{verbatim}
\versionadded{2.4}
\end{cfuncdesc}
The \member{tp_clear} handler must be of the \ctype{inquiry} type, or
\NULL{} if the object is immutable.
\begin{ctypedesc}[inquiry]{int (*inquiry)(PyObject *self)}
Drop references that may have created reference cycles. Immutable
objects do not have to define this method since they can never
directly create reference cycles. Note that the object must still
be valid after calling this method (don't just call
\cfunction{Py_DECREF()} on a reference). The collector will call
this method if it detects that this object is involved in a
reference cycle.
\end{ctypedesc}