summaryrefslogtreecommitdiff
path: root/sys/src/cmd/python/Doc/api/utilities.tex
diff options
context:
space:
mode:
authorcinap_lenrek <cinap_lenrek@localhost>2011-05-03 11:25:13 +0000
committercinap_lenrek <cinap_lenrek@localhost>2011-05-03 11:25:13 +0000
commit458120dd40db6b4df55a4e96b650e16798ef06a0 (patch)
tree8f82685be24fef97e715c6f5ca4c68d34d5074ee /sys/src/cmd/python/Doc/api/utilities.tex
parent3a742c699f6806c1145aea5149bf15de15a0afd7 (diff)
add hg and python
Diffstat (limited to 'sys/src/cmd/python/Doc/api/utilities.tex')
-rw-r--r--sys/src/cmd/python/Doc/api/utilities.tex1023
1 files changed, 1023 insertions, 0 deletions
diff --git a/sys/src/cmd/python/Doc/api/utilities.tex b/sys/src/cmd/python/Doc/api/utilities.tex
new file mode 100644
index 000000000..93e379645
--- /dev/null
+++ b/sys/src/cmd/python/Doc/api/utilities.tex
@@ -0,0 +1,1023 @@
+\chapter{Utilities \label{utilities}}
+
+The functions in this chapter perform various utility tasks, ranging
+from helping C code be more portable across platforms, using Python
+modules from C, and parsing function arguments and constructing Python
+values from C values.
+
+
+\section{Operating System Utilities \label{os}}
+
+\begin{cfuncdesc}{int}{Py_FdIsInteractive}{FILE *fp, const char *filename}
+ Return true (nonzero) if the standard I/O file \var{fp} with name
+ \var{filename} is deemed interactive. This is the case for files
+ for which \samp{isatty(fileno(\var{fp}))} is true. If the global
+ flag \cdata{Py_InteractiveFlag} is true, this function also returns
+ true if the \var{filename} pointer is \NULL{} or if the name is
+ equal to one of the strings \code{'<stdin>'} or \code{'???'}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{long}{PyOS_GetLastModificationTime}{char *filename}
+ Return the time of last modification of the file \var{filename}.
+ The result is encoded in the same way as the timestamp returned by
+ the standard C library function \cfunction{time()}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{PyOS_AfterFork}{}
+ Function to update some internal state after a process fork; this
+ should be called in the new process if the Python interpreter will
+ continue to be used. If a new executable is loaded into the new
+ process, this function does not need to be called.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyOS_CheckStack}{}
+ Return true when the interpreter runs out of stack space. This is a
+ reliable check, but is only available when \constant{USE_STACKCHECK}
+ is defined (currently on Windows using the Microsoft Visual \Cpp{}
+ compiler). \constant{USE_STACKCHECK} will be
+ defined automatically; you should never change the definition in
+ your own code.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyOS_sighandler_t}{PyOS_getsig}{int i}
+ Return the current signal handler for signal \var{i}. This is a
+ thin wrapper around either \cfunction{sigaction()} or
+ \cfunction{signal()}. Do not call those functions directly!
+ \ctype{PyOS_sighandler_t} is a typedef alias for \ctype{void
+ (*)(int)}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyOS_sighandler_t}{PyOS_setsig}{int i, PyOS_sighandler_t h}
+ Set the signal handler for signal \var{i} to be \var{h}; return the
+ old signal handler. This is a thin wrapper around either
+ \cfunction{sigaction()} or \cfunction{signal()}. Do not call those
+ functions directly! \ctype{PyOS_sighandler_t} is a typedef alias
+ for \ctype{void (*)(int)}.
+\end{cfuncdesc}
+
+
+\section{Process Control \label{processControl}}
+
+\begin{cfuncdesc}{void}{Py_FatalError}{const char *message}
+ Print a fatal error message and kill the process. No cleanup is
+ performed. This function should only be invoked when a condition is
+ detected that would make it dangerous to continue using the Python
+ interpreter; e.g., when the object administration appears to be
+ corrupted. On \UNIX, the standard C library function
+ \cfunction{abort()}\ttindex{abort()} is called which will attempt to
+ produce a \file{core} file.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{Py_Exit}{int status}
+ Exit the current process. This calls
+ \cfunction{Py_Finalize()}\ttindex{Py_Finalize()} and then calls the
+ standard C library function
+ \code{exit(\var{status})}\ttindex{exit()}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{Py_AtExit}{void (*func) ()}
+ Register a cleanup function to be called by
+ \cfunction{Py_Finalize()}\ttindex{Py_Finalize()}. The cleanup
+ function will be called with no arguments and should return no
+ value. At most 32 \index{cleanup functions}cleanup functions can be
+ registered. When the registration is successful,
+ \cfunction{Py_AtExit()} returns \code{0}; on failure, it returns
+ \code{-1}. The cleanup function registered last is called first.
+ Each cleanup function will be called at most once. Since Python's
+ internal finalization will have completed before the cleanup
+ function, no Python APIs should be called by \var{func}.
+\end{cfuncdesc}
+
+
+\section{Importing Modules \label{importing}}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_ImportModule}{const char *name}
+ This is a simplified interface to
+ \cfunction{PyImport_ImportModuleEx()} below, leaving the
+ \var{globals} and \var{locals} arguments set to \NULL. When the
+ \var{name} argument contains a dot (when it specifies a submodule of
+ a package), the \var{fromlist} argument is set to the list
+ \code{['*']} so that the return value is the named module rather
+ than the top-level package containing it as would otherwise be the
+ case. (Unfortunately, this has an additional side effect when
+ \var{name} in fact specifies a subpackage instead of a submodule:
+ the submodules specified in the package's \code{__all__} variable
+ are \index{package variable!\code{__all__}}
+ \withsubitem{(package variable)}{\ttindex{__all__}}loaded.) Return
+ a new reference to the imported module, or \NULL{} with an exception
+ set on failure. Before Python 2.4, the module may still be created in
+ the failure case --- examine \code{sys.modules} to find out. Starting
+ with Python 2.4, a failing import of a module no longer leaves the
+ module in \code{sys.modules}.
+ \versionchanged[failing imports remove incomplete module objects]{2.4}
+ \withsubitem{(in module sys)}{\ttindex{modules}}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_ImportModuleEx}{char *name,
+ PyObject *globals, PyObject *locals, PyObject *fromlist}
+ Import a module. This is best described by referring to the
+ built-in Python function
+ \function{__import__()}\bifuncindex{__import__}, as the standard
+ \function{__import__()} function calls this function directly.
+
+ The return value is a new reference to the imported module or
+ top-level package, or \NULL{} with an exception set on failure (before
+ Python 2.4, the
+ module may still be created in this case). Like for
+ \function{__import__()}, the return value when a submodule of a
+ package was requested is normally the top-level package, unless a
+ non-empty \var{fromlist} was given.
+ \versionchanged[failing imports remove incomplete module objects]{2.4}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_Import}{PyObject *name}
+ This is a higher-level interface that calls the current ``import
+ hook function''. It invokes the \function{__import__()} function
+ from the \code{__builtins__} of the current globals. This means
+ that the import is done using whatever import hooks are installed in
+ the current environment, e.g. by \module{rexec}\refstmodindex{rexec}
+ or \module{ihooks}\refstmodindex{ihooks}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_ReloadModule}{PyObject *m}
+ Reload a module. This is best described by referring to the
+ built-in Python function \function{reload()}\bifuncindex{reload}, as
+ the standard \function{reload()} function calls this function
+ directly. Return a new reference to the reloaded module, or \NULL{}
+ with an exception set on failure (the module still exists in this
+ case).
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_AddModule}{const char *name}
+ Return the module object corresponding to a module name. The
+ \var{name} argument may be of the form \code{package.module}.
+ First check the modules dictionary if there's one there, and if not,
+ create a new one and insert it in the modules dictionary.
+ Return \NULL{} with an exception set on failure.
+ \note{This function does not load or import the module; if the
+ module wasn't already loaded, you will get an empty module object.
+ Use \cfunction{PyImport_ImportModule()} or one of its variants to
+ import a module. Package structures implied by a dotted name for
+ \var{name} are not created if not already present.}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_ExecCodeModule}{char *name, PyObject *co}
+ Given a module name (possibly of the form \code{package.module}) and
+ a code object read from a Python bytecode file or obtained from the
+ built-in function \function{compile()}\bifuncindex{compile}, load
+ the module. Return a new reference to the module object, or \NULL{}
+ with an exception set if an error occurred. Before Python 2.4, the module
+ could still be created in error cases. Starting with Python 2.4,
+ \var{name} is removed from \code{sys.modules} in error cases, and even
+ if \var{name} was already in \code{sys.modules} on entry to
+ \cfunction{PyImport_ExecCodeModule()}. Leaving incompletely initialized
+ modules in \code{sys.modules} is dangerous, as imports of such modules
+ have no way to know that the module object is an unknown (and probably
+ damaged with respect to the module author's intents) state.
+
+ This function will reload the module if it was already imported. See
+ \cfunction{PyImport_ReloadModule()} for the intended way to reload a
+ module.
+
+ If \var{name} points to a dotted name of the
+ form \code{package.module}, any package structures not already
+ created will still not be created.
+
+ \versionchanged[\var{name} is removed from \code{sys.modules} in error cases]{2.4}
+
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{long}{PyImport_GetMagicNumber}{}
+ Return the magic number for Python bytecode files
+ (a.k.a. \file{.pyc} and \file{.pyo} files). The magic number should
+ be present in the first four bytes of the bytecode file, in
+ little-endian byte order.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyImport_GetModuleDict}{}
+ Return the dictionary used for the module administration
+ (a.k.a.\ \code{sys.modules}). Note that this is a per-interpreter
+ variable.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{_PyImport_Init}{}
+ Initialize the import mechanism. For internal use only.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{PyImport_Cleanup}{}
+ Empty the module table. For internal use only.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{_PyImport_Fini}{}
+ Finalize the import mechanism. For internal use only.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{_PyImport_FindExtension}{char *, char *}
+ For internal use only.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{_PyImport_FixupExtension}{char *, char *}
+ For internal use only.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyImport_ImportFrozenModule}{char *name}
+ Load a frozen module named \var{name}. Return \code{1} for success,
+ \code{0} if the module is not found, and \code{-1} with an exception
+ set if the initialization failed. To access the imported module on
+ a successful load, use \cfunction{PyImport_ImportModule()}. (Note
+ the misnomer --- this function would reload the module if it was
+ already imported.)
+\end{cfuncdesc}
+
+\begin{ctypedesc}[_frozen]{struct _frozen}
+ This is the structure type definition for frozen module descriptors,
+ as generated by the \program{freeze}\index{freeze utility} utility
+ (see \file{Tools/freeze/} in the Python source distribution). Its
+ definition, found in \file{Include/import.h}, is:
+
+\begin{verbatim}
+struct _frozen {
+ char *name;
+ unsigned char *code;
+ int size;
+};
+\end{verbatim}
+\end{ctypedesc}
+
+\begin{cvardesc}{struct _frozen*}{PyImport_FrozenModules}
+ This pointer is initialized to point to an array of \ctype{struct
+ _frozen} records, terminated by one whose members are all \NULL{} or
+ zero. When a frozen module is imported, it is searched in this
+ table. Third-party code could play tricks with this to provide a
+ dynamically created collection of frozen modules.
+\end{cvardesc}
+
+\begin{cfuncdesc}{int}{PyImport_AppendInittab}{char *name,
+ void (*initfunc)(void)}
+ Add a single module to the existing table of built-in modules. This
+ is a convenience wrapper around
+ \cfunction{PyImport_ExtendInittab()}, returning \code{-1} if the
+ table could not be extended. The new module can be imported by the
+ name \var{name}, and uses the function \var{initfunc} as the
+ initialization function called on the first attempted import. This
+ should be called before \cfunction{Py_Initialize()}.
+\end{cfuncdesc}
+
+\begin{ctypedesc}[_inittab]{struct _inittab}
+ Structure describing a single entry in the list of built-in
+ modules. Each of these structures gives the name and initialization
+ function for a module built into the interpreter. Programs which
+ embed Python may use an array of these structures in conjunction
+ with \cfunction{PyImport_ExtendInittab()} to provide additional
+ built-in modules. The structure is defined in
+ \file{Include/import.h} as:
+
+\begin{verbatim}
+struct _inittab {
+ char *name;
+ void (*initfunc)(void);
+};
+\end{verbatim}
+\end{ctypedesc}
+
+\begin{cfuncdesc}{int}{PyImport_ExtendInittab}{struct _inittab *newtab}
+ Add a collection of modules to the table of built-in modules. The
+ \var{newtab} array must end with a sentinel entry which contains
+ \NULL{} for the \member{name} field; failure to provide the sentinel
+ value can result in a memory fault. Returns \code{0} on success or
+ \code{-1} if insufficient memory could be allocated to extend the
+ internal table. In the event of failure, no modules are added to
+ the internal table. This should be called before
+ \cfunction{Py_Initialize()}.
+\end{cfuncdesc}
+
+
+\section{Data marshalling support \label{marshalling-utils}}
+
+These routines allow C code to work with serialized objects using the
+same data format as the \module{marshal} module. There are functions
+to write data into the serialization format, and additional functions
+that can be used to read the data back. Files used to store marshalled
+data must be opened in binary mode.
+
+Numeric values are stored with the least significant byte first.
+
+The module supports two versions of the data format: version 0 is the
+historical version, version 1 (new in Python 2.4) shares interned
+strings in the file, and upon unmarshalling. \var{Py_MARSHAL_VERSION}
+indicates the current file format (currently 1).
+
+\begin{cfuncdesc}{void}{PyMarshal_WriteLongToFile}{long value, FILE *file, int version}
+ Marshal a \ctype{long} integer, \var{value}, to \var{file}. This
+ will only write the least-significant 32 bits of \var{value};
+ regardless of the size of the native \ctype{long} type.
+
+ \versionchanged[\var{version} indicates the file format]{2.4}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{void}{PyMarshal_WriteObjectToFile}{PyObject *value,
+ FILE *file, int version}
+ Marshal a Python object, \var{value}, to \var{file}.
+
+ \versionchanged[\var{version} indicates the file format]{2.4}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyMarshal_WriteObjectToString}{PyObject *value, int version}
+ Return a string object containing the marshalled representation of
+ \var{value}.
+
+ \versionchanged[\var{version} indicates the file format]{2.4}
+\end{cfuncdesc}
+
+The following functions allow marshalled values to be read back in.
+
+XXX What about error detection? It appears that reading past the end
+of the file will always result in a negative numeric value (where
+that's relevant), but it's not clear that negative values won't be
+handled properly when there's no error. What's the right way to tell?
+Should only non-negative values be written using these routines?
+
+\begin{cfuncdesc}{long}{PyMarshal_ReadLongFromFile}{FILE *file}
+ Return a C \ctype{long} from the data stream in a \ctype{FILE*}
+ opened for reading. Only a 32-bit value can be read in using
+ this function, regardless of the native size of \ctype{long}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyMarshal_ReadShortFromFile}{FILE *file}
+ Return a C \ctype{short} from the data stream in a \ctype{FILE*}
+ opened for reading. Only a 16-bit value can be read in using
+ this function, regardless of the native size of \ctype{short}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyMarshal_ReadObjectFromFile}{FILE *file}
+ Return a Python object from the data stream in a \ctype{FILE*}
+ opened for reading. On error, sets the appropriate exception
+ (\exception{EOFError} or \exception{TypeError}) and returns \NULL.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyMarshal_ReadLastObjectFromFile}{FILE *file}
+ Return a Python object from the data stream in a \ctype{FILE*}
+ opened for reading. Unlike
+ \cfunction{PyMarshal_ReadObjectFromFile()}, this function assumes
+ that no further objects will be read from the file, allowing it to
+ aggressively load file data into memory so that the de-serialization
+ can operate from data in memory rather than reading a byte at a time
+ from the file. Only use these variant if you are certain that you
+ won't be reading anything else from the file. On error, sets the
+ appropriate exception (\exception{EOFError} or
+ \exception{TypeError}) and returns \NULL.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyMarshal_ReadObjectFromString}{char *string,
+ Py_ssize_t len}
+ Return a Python object from the data stream in a character buffer
+ containing \var{len} bytes pointed to by \var{string}. On error,
+ sets the appropriate exception (\exception{EOFError} or
+ \exception{TypeError}) and returns \NULL.
+\end{cfuncdesc}
+
+
+\section{Parsing arguments and building values
+ \label{arg-parsing}}
+
+These functions are useful when creating your own extensions functions
+and methods. Additional information and examples are available in
+\citetitle[../ext/ext.html]{Extending and Embedding the Python
+Interpreter}.
+
+The first three of these functions described,
+\cfunction{PyArg_ParseTuple()},
+\cfunction{PyArg_ParseTupleAndKeywords()}, and
+\cfunction{PyArg_Parse()}, all use \emph{format strings} which are
+used to tell the function about the expected arguments. The format
+strings use the same syntax for each of these functions.
+
+A format string consists of zero or more ``format units.'' A format
+unit describes one Python object; it is usually a single character or
+a parenthesized sequence of format units. With a few exceptions, a
+format unit that is not a parenthesized sequence normally corresponds
+to a single address argument to these functions. In the following
+description, the quoted form is the format unit; the entry in (round)
+parentheses is the Python object type that matches the format unit;
+and the entry in [square] brackets is the type of the C variable(s)
+whose address should be passed.
+
+\begin{description}
+ \item[\samp{s} (string or Unicode object) {[const char *]}]
+ Convert a Python string or Unicode object to a C pointer to a
+ character string. You must not provide storage for the string
+ itself; a pointer to an existing string is stored into the character
+ pointer variable whose address you pass. The C string is
+ NUL-terminated. The Python string must not contain embedded NUL
+ bytes; if it does, a \exception{TypeError} exception is raised.
+ Unicode objects are converted to C strings using the default
+ encoding. If this conversion fails, a \exception{UnicodeError} is
+ raised.
+
+ \item[\samp{s\#} (string, Unicode or any read buffer compatible object)
+ {[const char *, int]}]
+ This variant on \samp{s} stores into two C variables, the first one
+ a pointer to a character string, the second one its length. In this
+ case the Python string may contain embedded null bytes. Unicode
+ objects pass back a pointer to the default encoded string version of
+ the object if such a conversion is possible. All other read-buffer
+ compatible objects pass back a reference to the raw internal data
+ representation.
+
+ \item[\samp{z} (string or \code{None}) {[const char *]}]
+ Like \samp{s}, but the Python object may also be \code{None}, in
+ which case the C pointer is set to \NULL.
+
+ \item[\samp{z\#} (string or \code{None} or any read buffer
+ compatible object) {[const char *, int]}]
+ This is to \samp{s\#} as \samp{z} is to \samp{s}.
+
+ \item[\samp{u} (Unicode object) {[Py_UNICODE *]}]
+ Convert a Python Unicode object to a C pointer to a NUL-terminated
+ buffer of 16-bit Unicode (UTF-16) data. As with \samp{s}, there is
+ no need to provide storage for the Unicode data buffer; a pointer to
+ the existing Unicode data is stored into the \ctype{Py_UNICODE}
+ pointer variable whose address you pass.
+
+ \item[\samp{u\#} (Unicode object) {[Py_UNICODE *, int]}]
+ This variant on \samp{u} stores into two C variables, the first one
+ a pointer to a Unicode data buffer, the second one its length.
+ Non-Unicode objects are handled by interpreting their read-buffer
+ pointer as pointer to a \ctype{Py_UNICODE} array.
+
+ \item[\samp{es} (string, Unicode object or character buffer
+ compatible object) {[const char *encoding, char **buffer]}]
+ This variant on \samp{s} is used for encoding Unicode and objects
+ convertible to Unicode into a character buffer. It only works for
+ encoded data without embedded NUL bytes.
+
+ This format requires two arguments. The first is only used as
+ input, and must be a \ctype{const char*} which points to the name of an
+ encoding as a NUL-terminated string, or \NULL, in which case the
+ default encoding is used. An exception is raised if the named
+ encoding is not known to Python. The second argument must be a
+ \ctype{char**}; the value of the pointer it references will be set
+ to a buffer with the contents of the argument text. The text will
+ be encoded in the encoding specified by the first argument.
+
+ \cfunction{PyArg_ParseTuple()} will allocate a buffer of the needed
+ size, copy the encoded data into this buffer and adjust
+ \var{*buffer} to reference the newly allocated storage. The caller
+ is responsible for calling \cfunction{PyMem_Free()} to free the
+ allocated buffer after use.
+
+ \item[\samp{et} (string, Unicode object or character buffer
+ compatible object) {[const char *encoding, char **buffer]}]
+ Same as \samp{es} except that 8-bit string objects are passed
+ through without recoding them. Instead, the implementation assumes
+ that the string object uses the encoding passed in as parameter.
+
+ \item[\samp{es\#} (string, Unicode object or character buffer compatible
+ object) {[const char *encoding, char **buffer, int *buffer_length]}]
+ This variant on \samp{s\#} is used for encoding Unicode and objects
+ convertible to Unicode into a character buffer. Unlike the
+ \samp{es} format, this variant allows input data which contains NUL
+ characters.
+
+ It requires three arguments. The first is only used as input, and
+ must be a \ctype{const char*} which points to the name of an encoding as a
+ NUL-terminated string, or \NULL, in which case the default encoding
+ is used. An exception is raised if the named encoding is not known
+ to Python. The second argument must be a \ctype{char**}; the value
+ of the pointer it references will be set to a buffer with the
+ contents of the argument text. The text will be encoded in the
+ encoding specified by the first argument. The third argument must
+ be a pointer to an integer; the referenced integer will be set to
+ the number of bytes in the output buffer.
+
+ There are two modes of operation:
+
+ If \var{*buffer} points a \NULL{} pointer, the function will
+ allocate a buffer of the needed size, copy the encoded data into
+ this buffer and set \var{*buffer} to reference the newly allocated
+ storage. The caller is responsible for calling
+ \cfunction{PyMem_Free()} to free the allocated buffer after usage.
+
+ If \var{*buffer} points to a non-\NULL{} pointer (an already
+ allocated buffer), \cfunction{PyArg_ParseTuple()} will use this
+ location as the buffer and interpret the initial value of
+ \var{*buffer_length} as the buffer size. It will then copy the
+ encoded data into the buffer and NUL-terminate it. If the buffer
+ is not large enough, a \exception{ValueError} will be set.
+
+ In both cases, \var{*buffer_length} is set to the length of the
+ encoded data without the trailing NUL byte.
+
+ \item[\samp{et\#} (string, Unicode object or character buffer compatible
+ object) {[const char *encoding, char **buffer]}]
+ Same as \samp{es\#} except that string objects are passed through
+ without recoding them. Instead, the implementation assumes that the
+ string object uses the encoding passed in as parameter.
+
+ \item[\samp{b} (integer) {[char]}]
+ Convert a Python integer to a tiny int, stored in a C \ctype{char}.
+
+ \item[\samp{B} (integer) {[unsigned char]}]
+ Convert a Python integer to a tiny int without overflow checking,
+ stored in a C \ctype{unsigned char}. \versionadded{2.3}
+
+ \item[\samp{h} (integer) {[short int]}]
+ Convert a Python integer to a C \ctype{short int}.
+
+ \item[\samp{H} (integer) {[unsigned short int]}]
+ Convert a Python integer to a C \ctype{unsigned short int}, without
+ overflow checking. \versionadded{2.3}
+
+ \item[\samp{i} (integer) {[int]}]
+ Convert a Python integer to a plain C \ctype{int}.
+
+ \item[\samp{I} (integer) {[unsigned int]}]
+ Convert a Python integer to a C \ctype{unsigned int}, without
+ overflow checking. \versionadded{2.3}
+
+ \item[\samp{l} (integer) {[long int]}]
+ Convert a Python integer to a C \ctype{long int}.
+
+ \item[\samp{k} (integer) {[unsigned long]}]
+ Convert a Python integer or long integer to a C \ctype{unsigned long} without
+ overflow checking. \versionadded{2.3}
+
+ \item[\samp{L} (integer) {[PY_LONG_LONG]}]
+ Convert a Python integer to a C \ctype{long long}. This format is
+ only available on platforms that support \ctype{long long} (or
+ \ctype{_int64} on Windows).
+
+ \item[\samp{K} (integer) {[unsigned PY_LONG_LONG]}]
+ Convert a Python integer or long integer to a C \ctype{unsigned long long}
+ without overflow checking. This format is only available on
+ platforms that support \ctype{unsigned long long} (or
+ \ctype{unsigned _int64} on Windows). \versionadded{2.3}
+
+ \item[\samp{n} (integer) {[Py_ssize_t]}]
+ Convert a Python integer or long integer to a C \ctype{Py_ssize_t}.
+ \versionadded{2.5}
+
+ \item[\samp{c} (string of length 1) {[char]}]
+ Convert a Python character, represented as a string of length 1, to
+ a C \ctype{char}.
+
+ \item[\samp{f} (float) {[float]}]
+ Convert a Python floating point number to a C \ctype{float}.
+
+ \item[\samp{d} (float) {[double]}]
+ Convert a Python floating point number to a C \ctype{double}.
+
+ \item[\samp{D} (complex) {[Py_complex]}]
+ Convert a Python complex number to a C \ctype{Py_complex} structure.
+
+ \item[\samp{O} (object) {[PyObject *]}]
+ Store a Python object (without any conversion) in a C object
+ pointer. The C program thus receives the actual object that was
+ passed. The object's reference count is not increased. The pointer
+ stored is not \NULL.
+
+ \item[\samp{O!} (object) {[\var{typeobject}, PyObject *]}]
+ Store a Python object in a C object pointer. This is similar to
+ \samp{O}, but takes two C arguments: the first is the address of a
+ Python type object, the second is the address of the C variable (of
+ type \ctype{PyObject*}) into which the object pointer is stored. If
+ the Python object does not have the required type,
+ \exception{TypeError} is raised.
+
+ \item[\samp{O\&} (object) {[\var{converter}, \var{anything}]}]
+ Convert a Python object to a C variable through a \var{converter}
+ function. This takes two arguments: the first is a function, the
+ second is the address of a C variable (of arbitrary type), converted
+ to \ctype{void *}. The \var{converter} function in turn is called
+ as follows:
+
+ \var{status}\code{ = }\var{converter}\code{(}\var{object},
+ \var{address}\code{);}
+
+ where \var{object} is the Python object to be converted and
+ \var{address} is the \ctype{void*} argument that was passed to the
+ \cfunction{PyArg_Parse*()} function. The returned \var{status}
+ should be \code{1} for a successful conversion and \code{0} if the
+ conversion has failed. When the conversion fails, the
+ \var{converter} function should raise an exception.
+
+ \item[\samp{S} (string) {[PyStringObject *]}]
+ Like \samp{O} but requires that the Python object is a string
+ object. Raises \exception{TypeError} if the object is not a string
+ object. The C variable may also be declared as \ctype{PyObject*}.
+
+ \item[\samp{U} (Unicode string) {[PyUnicodeObject *]}]
+ Like \samp{O} but requires that the Python object is a Unicode
+ object. Raises \exception{TypeError} if the object is not a Unicode
+ object. The C variable may also be declared as \ctype{PyObject*}.
+
+ \item[\samp{t\#} (read-only character buffer) {[char *, int]}]
+ Like \samp{s\#}, but accepts any object which implements the
+ read-only buffer interface. The \ctype{char*} variable is set to
+ point to the first byte of the buffer, and the \ctype{int} is set to
+ the length of the buffer. Only single-segment buffer objects are
+ accepted; \exception{TypeError} is raised for all others.
+
+ \item[\samp{w} (read-write character buffer) {[char *]}]
+ Similar to \samp{s}, but accepts any object which implements the
+ read-write buffer interface. The caller must determine the length
+ of the buffer by other means, or use \samp{w\#} instead. Only
+ single-segment buffer objects are accepted; \exception{TypeError} is
+ raised for all others.
+
+ \item[\samp{w\#} (read-write character buffer) {[char *, int]}]
+ Like \samp{s\#}, but accepts any object which implements the
+ read-write buffer interface. The \ctype{char *} variable is set to
+ point to the first byte of the buffer, and the \ctype{int} is set to
+ the length of the buffer. Only single-segment buffer objects are
+ accepted; \exception{TypeError} is raised for all others.
+
+ \item[\samp{(\var{items})} (tuple) {[\var{matching-items}]}]
+ The object must be a Python sequence whose length is the number of
+ format units in \var{items}. The C arguments must correspond to the
+ individual format units in \var{items}. Format units for sequences
+ may be nested.
+
+ \note{Prior to Python version 1.5.2, this format specifier only
+ accepted a tuple containing the individual parameters, not an
+ arbitrary sequence. Code which previously caused
+ \exception{TypeError} to be raised here may now proceed without an
+ exception. This is not expected to be a problem for existing code.}
+\end{description}
+
+It is possible to pass Python long integers where integers are
+requested; however no proper range checking is done --- the most
+significant bits are silently truncated when the receiving field is
+too small to receive the value (actually, the semantics are inherited
+from downcasts in C --- your mileage may vary).
+
+A few other characters have a meaning in a format string. These may
+not occur inside nested parentheses. They are:
+
+\begin{description}
+ \item[\samp{|}]
+ Indicates that the remaining arguments in the Python argument list
+ are optional. The C variables corresponding to optional arguments
+ should be initialized to their default value --- when an optional
+ argument is not specified, \cfunction{PyArg_ParseTuple()} does not
+ touch the contents of the corresponding C variable(s).
+
+ \item[\samp{:}]
+ The list of format units ends here; the string after the colon is
+ used as the function name in error messages (the ``associated
+ value'' of the exception that \cfunction{PyArg_ParseTuple()}
+ raises).
+
+ \item[\samp{;}]
+ The list of format units ends here; the string after the semicolon
+ is used as the error message \emph{instead} of the default error
+ message. Clearly, \samp{:} and \samp{;} mutually exclude each
+ other.
+\end{description}
+
+Note that any Python object references which are provided to the
+caller are \emph{borrowed} references; do not decrement their
+reference count!
+
+Additional arguments passed to these functions must be addresses of
+variables whose type is determined by the format string; these are
+used to store values from the input tuple. There are a few cases, as
+described in the list of format units above, where these parameters
+are used as input values; they should match what is specified for the
+corresponding format unit in that case.
+
+For the conversion to succeed, the \var{arg} object must match the
+format and the format must be exhausted. On success, the
+\cfunction{PyArg_Parse*()} functions return true, otherwise they
+return false and raise an appropriate exception.
+
+\begin{cfuncdesc}{int}{PyArg_ParseTuple}{PyObject *args, const char *format,
+ \moreargs}
+ Parse the parameters of a function that takes only positional
+ parameters into local variables. Returns true on success; on
+ failure, it returns false and raises the appropriate exception.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyArg_VaParse}{PyObject *args, const char *format,
+ va_list vargs}
+ Identical to \cfunction{PyArg_ParseTuple()}, except that it accepts a
+ va_list rather than a variable number of arguments.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyArg_ParseTupleAndKeywords}{PyObject *args,
+ PyObject *kw, const char *format, char *keywords[],
+ \moreargs}
+ Parse the parameters of a function that takes both positional and
+ keyword parameters into local variables. Returns true on success;
+ on failure, it returns false and raises the appropriate exception.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyArg_VaParseTupleAndKeywords}{PyObject *args,
+ PyObject *kw, const char *format, char *keywords[],
+ va_list vargs}
+ Identical to \cfunction{PyArg_ParseTupleAndKeywords()}, except that it
+ accepts a va_list rather than a variable number of arguments.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyArg_Parse}{PyObject *args, const char *format,
+ \moreargs}
+ Function used to deconstruct the argument lists of ``old-style''
+ functions --- these are functions which use the
+ \constant{METH_OLDARGS} parameter parsing method. This is not
+ recommended for use in parameter parsing in new code, and most code
+ in the standard interpreter has been modified to no longer use this
+ for that purpose. It does remain a convenient way to decompose
+ other tuples, however, and may continue to be used for that
+ purpose.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyArg_UnpackTuple}{PyObject *args, const char *name,
+ Py_ssize_t min, Py_ssize_t max, \moreargs}
+ A simpler form of parameter retrieval which does not use a format
+ string to specify the types of the arguments. Functions which use
+ this method to retrieve their parameters should be declared as
+ \constant{METH_VARARGS} in function or method tables. The tuple
+ containing the actual parameters should be passed as \var{args}; it
+ must actually be a tuple. The length of the tuple must be at least
+ \var{min} and no more than \var{max}; \var{min} and \var{max} may be
+ equal. Additional arguments must be passed to the function, each of
+ which should be a pointer to a \ctype{PyObject*} variable; these
+ will be filled in with the values from \var{args}; they will contain
+ borrowed references. The variables which correspond to optional
+ parameters not given by \var{args} will not be filled in; these
+ should be initialized by the caller.
+ This function returns true on success and false if \var{args} is not
+ a tuple or contains the wrong number of elements; an exception will
+ be set if there was a failure.
+
+ This is an example of the use of this function, taken from the
+ sources for the \module{_weakref} helper module for weak references:
+
+\begin{verbatim}
+static PyObject *
+weakref_ref(PyObject *self, PyObject *args)
+{
+ PyObject *object;
+ PyObject *callback = NULL;
+ PyObject *result = NULL;
+
+ if (PyArg_UnpackTuple(args, "ref", 1, 2, &object, &callback)) {
+ result = PyWeakref_NewRef(object, callback);
+ }
+ return result;
+}
+\end{verbatim}
+
+ The call to \cfunction{PyArg_UnpackTuple()} in this example is
+ entirely equivalent to this call to \cfunction{PyArg_ParseTuple()}:
+
+\begin{verbatim}
+PyArg_ParseTuple(args, "O|O:ref", &object, &callback)
+\end{verbatim}
+
+ \versionadded{2.2}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{Py_BuildValue}{const char *format,
+ \moreargs}
+ Create a new value based on a format string similar to those
+ accepted by the \cfunction{PyArg_Parse*()} family of functions and a
+ sequence of values. Returns the value or \NULL{} in the case of an
+ error; an exception will be raised if \NULL{} is returned.
+
+ \cfunction{Py_BuildValue()} does not always build a tuple. It
+ builds a tuple only if its format string contains two or more format
+ units. If the format string is empty, it returns \code{None}; if it
+ contains exactly one format unit, it returns whatever object is
+ described by that format unit. To force it to return a tuple of
+ size 0 or one, parenthesize the format string.
+
+ When memory buffers are passed as parameters to supply data to build
+ objects, as for the \samp{s} and \samp{s\#} formats, the required
+ data is copied. Buffers provided by the caller are never referenced
+ by the objects created by \cfunction{Py_BuildValue()}. In other
+ words, if your code invokes \cfunction{malloc()} and passes the
+ allocated memory to \cfunction{Py_BuildValue()}, your code is
+ responsible for calling \cfunction{free()} for that memory once
+ \cfunction{Py_BuildValue()} returns.
+
+ In the following description, the quoted form is the format unit;
+ the entry in (round) parentheses is the Python object type that the
+ format unit will return; and the entry in [square] brackets is the
+ type of the C value(s) to be passed.
+
+ The characters space, tab, colon and comma are ignored in format
+ strings (but not within format units such as \samp{s\#}). This can
+ be used to make long format strings a tad more readable.
+
+ \begin{description}
+ \item[\samp{s} (string) {[char *]}]
+ Convert a null-terminated C string to a Python object. If the C
+ string pointer is \NULL, \code{None} is used.
+
+ \item[\samp{s\#} (string) {[char *, int]}]
+ Convert a C string and its length to a Python object. If the C
+ string pointer is \NULL, the length is ignored and \code{None} is
+ returned.
+
+ \item[\samp{z} (string or \code{None}) {[char *]}]
+ Same as \samp{s}.
+
+ \item[\samp{z\#} (string or \code{None}) {[char *, int]}]
+ Same as \samp{s\#}.
+
+ \item[\samp{u} (Unicode string) {[Py_UNICODE *]}]
+ Convert a null-terminated buffer of Unicode (UCS-2 or UCS-4)
+ data to a Python Unicode object. If the Unicode buffer pointer
+ is \NULL, \code{None} is returned.
+
+ \item[\samp{u\#} (Unicode string) {[Py_UNICODE *, int]}]
+ Convert a Unicode (UCS-2 or UCS-4) data buffer and its length
+ to a Python Unicode object. If the Unicode buffer pointer
+ is \NULL, the length is ignored and \code{None} is returned.
+
+ \item[\samp{i} (integer) {[int]}]
+ Convert a plain C \ctype{int} to a Python integer object.
+
+ \item[\samp{b} (integer) {[char]}]
+ Convert a plain C \ctype{char} to a Python integer object.
+
+ \item[\samp{h} (integer) {[short int]}]
+ Convert a plain C \ctype{short int} to a Python integer object.
+
+ \item[\samp{l} (integer) {[long int]}]
+ Convert a C \ctype{long int} to a Python integer object.
+
+ \item[\samp{B} (integer) {[unsigned char]}]
+ Convert a C \ctype{unsigned char} to a Python integer object.
+
+ \item[\samp{H} (integer) {[unsigned short int]}]
+ Convert a C \ctype{unsigned short int} to a Python integer object.
+
+ \item[\samp{I} (integer/long) {[unsigned int]}]
+ Convert a C \ctype{unsigned int} to a Python integer object
+ or a Python long integer object, if it is larger than \code{sys.maxint}.
+
+ \item[\samp{k} (integer/long) {[unsigned long]}]
+ Convert a C \ctype{unsigned long} to a Python integer object
+ or a Python long integer object, if it is larger than \code{sys.maxint}.
+
+ \item[\samp{L} (long) {[PY_LONG_LONG]}]
+ Convert a C \ctype{long long} to a Python long integer object. Only
+ available on platforms that support \ctype{long long}.
+
+ \item[\samp{K} (long) {[unsigned PY_LONG_LONG]}]
+ Convert a C \ctype{unsigned long long} to a Python long integer object.
+ Only available on platforms that support \ctype{unsigned long long}.
+
+ \item[\samp{n} (int) {[Py_ssize_t]}]
+ Convert a C \ctype{Py_ssize_t} to a Python integer or long integer.
+ \versionadded{2.5}
+
+ \item[\samp{c} (string of length 1) {[char]}]
+ Convert a C \ctype{int} representing a character to a Python
+ string of length 1.
+
+ \item[\samp{d} (float) {[double]}]
+ Convert a C \ctype{double} to a Python floating point number.
+
+ \item[\samp{f} (float) {[float]}]
+ Same as \samp{d}.
+
+ \item[\samp{D} (complex) {[Py_complex *]}]
+ Convert a C \ctype{Py_complex} structure to a Python complex
+ number.
+
+ \item[\samp{O} (object) {[PyObject *]}]
+ Pass a Python object untouched (except for its reference count,
+ which is incremented by one). If the object passed in is a
+ \NULL{} pointer, it is assumed that this was caused because the
+ call producing the argument found an error and set an exception.
+ Therefore, \cfunction{Py_BuildValue()} will return \NULL{} but
+ won't raise an exception. If no exception has been raised yet,
+ \exception{SystemError} is set.
+
+ \item[\samp{S} (object) {[PyObject *]}]
+ Same as \samp{O}.
+
+ \item[\samp{N} (object) {[PyObject *]}]
+ Same as \samp{O}, except it doesn't increment the reference count
+ on the object. Useful when the object is created by a call to an
+ object constructor in the argument list.
+
+ \item[\samp{O\&} (object) {[\var{converter}, \var{anything}]}]
+ Convert \var{anything} to a Python object through a
+ \var{converter} function. The function is called with
+ \var{anything} (which should be compatible with \ctype{void *}) as
+ its argument and should return a ``new'' Python object, or \NULL{}
+ if an error occurred.
+
+ \item[\samp{(\var{items})} (tuple) {[\var{matching-items}]}]
+ Convert a sequence of C values to a Python tuple with the same
+ number of items.
+
+ \item[\samp{[\var{items}]} (list) {[\var{matching-items}]}]
+ Convert a sequence of C values to a Python list with the same
+ number of items.
+
+ \item[\samp{\{\var{items}\}} (dictionary) {[\var{matching-items}]}]
+ Convert a sequence of C values to a Python dictionary. Each pair
+ of consecutive C values adds one item to the dictionary, serving
+ as key and value, respectively.
+
+ \end{description}
+
+ If there is an error in the format string, the
+ \exception{SystemError} exception is set and \NULL{} returned.
+\end{cfuncdesc}
+
+\section{String conversion and formatting \label{string-formatting}}
+
+Functions for number conversion and formatted string output.
+
+\begin{cfuncdesc}{int}{PyOS_snprintf}{char *str, size_t size,
+ const char *format, \moreargs}
+Output not more than \var{size} bytes to \var{str} according to the format
+string \var{format} and the extra arguments. See the \UNIX{} man
+page \manpage{snprintf}{2}.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyOS_vsnprintf}{char *str, size_t size,
+ const char *format, va_list va}
+Output not more than \var{size} bytes to \var{str} according to the format
+string \var{format} and the variable argument list \var{va}. \UNIX{}
+man page \manpage{vsnprintf}{2}.
+\end{cfuncdesc}
+
+\cfunction{PyOS_snprintf} and \cfunction{PyOS_vsnprintf} wrap the
+Standard C library functions \cfunction{snprintf()} and
+\cfunction{vsnprintf()}. Their purpose is to guarantee consistent
+behavior in corner cases, which the Standard C functions do not.
+
+The wrappers ensure that \var{str}[\var{size}-1] is always
+\character{\textbackslash0} upon return. They never write more than
+\var{size} bytes (including the trailing \character{\textbackslash0}
+into str. Both functions require that \code{\var{str} != NULL},
+\code{\var{size} > 0} and \code{\var{format} != NULL}.
+
+If the platform doesn't have \cfunction{vsnprintf()} and the buffer
+size needed to avoid truncation exceeds \var{size} by more than 512
+bytes, Python aborts with a \var{Py_FatalError}.
+
+The return value (\var{rv}) for these functions should be interpreted
+as follows:
+
+\begin{itemize}
+
+\item When \code{0 <= \var{rv} < \var{size}}, the output conversion
+ was successful and \var{rv} characters were written to \var{str}
+ (excluding the trailing \character{\textbackslash0} byte at
+ \var{str}[\var{rv}]).
+
+\item When \code{\var{rv} >= \var{size}}, the output conversion was
+ truncated and a buffer with \code{\var{rv} + 1} bytes would have
+ been needed to succeed. \var{str}[\var{size}-1] is
+ \character{\textbackslash0} in this case.
+
+\item When \code{\var{rv} < 0}, ``something bad happened.''
+ \var{str}[\var{size}-1] is \character{\textbackslash0} in this case
+ too, but the rest of \var{str} is undefined. The exact cause of the
+ error depends on the underlying platform.
+
+\end{itemize}
+
+The following functions provide locale-independent string to number
+conversions.
+
+\begin{cfuncdesc}{double}{PyOS_ascii_strtod}{const char *nptr, char **endptr}
+Convert a string to a \ctype{double}. This function behaves like the
+Standard C function \cfunction{strtod()} does in the C locale. It does
+this without changing the current locale, since that would not be
+thread-safe.
+
+\cfunction{PyOS_ascii_strtod} should typically be used for reading
+configuration files or other non-user input that should be locale
+independent. \versionadded{2.4}
+
+See the \UNIX{} man page \manpage{strtod}{2} for details.
+
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{char *}{PyOS_ascii_formatd}{char *buffer, size_t buf_len,
+ const char *format, double d}
+Convert a \ctype{double} to a string using the \character{.} as the
+decimal separator. \var{format} is a \cfunction{printf()}-style format
+string specifying the number format. Allowed conversion characters are
+\character{e}, \character{E}, \character{f}, \character{F},
+\character{g} and \character{G}.
+
+The return value is a pointer to \var{buffer} with the converted
+string or NULL if the conversion failed. \versionadded{2.4}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{double}{PyOS_ascii_atof}{const char *nptr}
+Convert a string to a \ctype{double} in a locale-independent
+way. \versionadded{2.4}
+
+See the \UNIX{} man page \manpage{atof}{2} for details.
+\end{cfuncdesc}