source: trunk/essentials/dev-lang/python/Doc/api/init.tex@ 3226

\chapter{Initialization, Finalization, and Threads
         \label{initialization}}

\begin{cfuncdesc}{void}{Py_Initialize}{}
  Initialize the Python interpreter.  In an application embedding 
  Python, this should be called before using any other Python/C API
  functions; with the exception of
  \cfunction{Py_SetProgramName()}\ttindex{Py_SetProgramName()},
  \cfunction{PyEval_InitThreads()}\ttindex{PyEval_InitThreads()},
  \cfunction{PyEval_ReleaseLock()}\ttindex{PyEval_ReleaseLock()},
  and \cfunction{PyEval_AcquireLock()}\ttindex{PyEval_AcquireLock()}.
  This initializes the table of loaded modules (\code{sys.modules}),
  and\withsubitem{(in module sys)}{\ttindex{modules}\ttindex{path}}
  creates the fundamental modules
  \module{__builtin__}\refbimodindex{__builtin__},
  \module{__main__}\refbimodindex{__main__} and
  \module{sys}\refbimodindex{sys}.  It also initializes the module
  search\indexiii{module}{search}{path} path (\code{sys.path}).
  It does not set \code{sys.argv}; use
  \cfunction{PySys_SetArgv()}\ttindex{PySys_SetArgv()} for that.  This
  is a no-op when called for a second time (without calling
  \cfunction{Py_Finalize()}\ttindex{Py_Finalize()} first).  There is
  no return value; it is a fatal error if the initialization fails.
\end{cfuncdesc}

\begin{cfuncdesc}{void}{Py_InitializeEx}{int initsigs}
  This function works like \cfunction{Py_Initialize()} if
  \var{initsigs} is 1. If \var{initsigs} is 0, it skips
  initialization registration of signal handlers, which
  might be useful when Python is embedded. \versionadded{2.4}
\end{cfuncdesc}

\begin{cfuncdesc}{int}{Py_IsInitialized}{}
  Return true (nonzero) when the Python interpreter has been
  initialized, false (zero) if not.  After \cfunction{Py_Finalize()}
  is called, this returns false until \cfunction{Py_Initialize()} is
  called again.
\end{cfuncdesc}

\begin{cfuncdesc}{void}{Py_Finalize}{}
  Undo all initializations made by \cfunction{Py_Initialize()} and
  subsequent use of Python/C API functions, and destroy all
  sub-interpreters (see \cfunction{Py_NewInterpreter()} below) that
  were created and not yet destroyed since the last call to
  \cfunction{Py_Initialize()}.  Ideally, this frees all memory
  allocated by the Python interpreter.  This is a no-op when called
  for a second time (without calling \cfunction{Py_Initialize()} again
  first).  There is no return value; errors during finalization are
  ignored.

  This function is provided for a number of reasons.  An embedding
  application might want to restart Python without having to restart
  the application itself.  An application that has loaded the Python
  interpreter from a dynamically loadable library (or DLL) might want
  to free all memory allocated by Python before unloading the
  DLL. During a hunt for memory leaks in an application a developer
  might want to free all memory allocated by Python before exiting
  from the application.

  \strong{Bugs and caveats:} The destruction of modules and objects in
  modules is done in random order; this may cause destructors
  (\method{__del__()} methods) to fail when they depend on other
  objects (even functions) or modules.  Dynamically loaded extension
  modules loaded by Python are not unloaded.  Small amounts of memory
  allocated by the Python interpreter may not be freed (if you find a
  leak, please report it).  Memory tied up in circular references
  between objects is not freed.  Some memory allocated by extension
  modules may not be freed.  Some extensions may not work properly if
  their initialization routine is called more than once; this can
  happen if an application calls \cfunction{Py_Initialize()} and
  \cfunction{Py_Finalize()} more than once.
\end{cfuncdesc}

\begin{cfuncdesc}{PyThreadState*}{Py_NewInterpreter}{}
  Create a new sub-interpreter.  This is an (almost) totally separate
  environment for the execution of Python code.  In particular, the
  new interpreter has separate, independent versions of all imported
  modules, including the fundamental modules
  \module{__builtin__}\refbimodindex{__builtin__},
  \module{__main__}\refbimodindex{__main__} and
  \module{sys}\refbimodindex{sys}.  The table of loaded modules
  (\code{sys.modules}) and the module search path (\code{sys.path})
  are also separate.  The new environment has no \code{sys.argv}
  variable.  It has new standard I/O stream file objects
  \code{sys.stdin}, \code{sys.stdout} and \code{sys.stderr} (however
  these refer to the same underlying \ctype{FILE} structures in the C
  library).
  \withsubitem{(in module sys)}{
    \ttindex{stdout}\ttindex{stderr}\ttindex{stdin}}

  The return value points to the first thread state created in the new
  sub-interpreter.  This thread state is made in the current thread
  state.  Note that no actual thread is created; see the discussion of
  thread states below.  If creation of the new interpreter is
  unsuccessful, \NULL{} is returned; no exception is set since the
  exception state is stored in the current thread state and there may
  not be a current thread state.  (Like all other Python/C API
  functions, the global interpreter lock must be held before calling
  this function and is still held when it returns; however, unlike
  most other Python/C API functions, there needn't be a current thread
  state on entry.)

  Extension modules are shared between (sub-)interpreters as follows:
  the first time a particular extension is imported, it is initialized
  normally, and a (shallow) copy of its module's dictionary is
  squirreled away.  When the same extension is imported by another
  (sub-)interpreter, a new module is initialized and filled with the
  contents of this copy; the extension's \code{init} function is not
  called.  Note that this is different from what happens when an
  extension is imported after the interpreter has been completely
  re-initialized by calling
  \cfunction{Py_Finalize()}\ttindex{Py_Finalize()} and
  \cfunction{Py_Initialize()}\ttindex{Py_Initialize()}; in that case,
  the extension's \code{init\var{module}} function \emph{is} called
  again.

  \strong{Bugs and caveats:} Because sub-interpreters (and the main
  interpreter) are part of the same process, the insulation between
  them isn't perfect --- for example, using low-level file operations
  like \withsubitem{(in module os)}{\ttindex{close()}}
  \function{os.close()} they can (accidentally or maliciously) affect
  each other's open files.  Because of the way extensions are shared
  between (sub-)interpreters, some extensions may not work properly;
  this is especially likely when the extension makes use of (static)
  global variables, or when the extension manipulates its module's
  dictionary after its initialization.  It is possible to insert
  objects created in one sub-interpreter into a namespace of another
  sub-interpreter; this should be done with great care to avoid
  sharing user-defined functions, methods, instances or classes
  between sub-interpreters, since import operations executed by such
  objects may affect the wrong (sub-)interpreter's dictionary of
  loaded modules.  (XXX This is a hard-to-fix bug that will be
  addressed in a future release.)

  Also note that the use of this functionality is incompatible with
  extension modules such as PyObjC and ctypes that use the
  \cfunction{PyGILState_*} APIs (and this is inherent in the way the
  \cfunction{PyGILState_*} functions work).  Simple things may work,
  but confusing behavior will always be near.
\end{cfuncdesc}

\begin{cfuncdesc}{void}{Py_EndInterpreter}{PyThreadState *tstate}
  Destroy the (sub-)interpreter represented by the given thread state.
  The given thread state must be the current thread state.  See the
  discussion of thread states below.  When the call returns, the
  current thread state is \NULL.  All thread states associated with
  this interpreter are destroyed.  (The global interpreter lock must
  be held before calling this function and is still held when it
  returns.)  \cfunction{Py_Finalize()}\ttindex{Py_Finalize()} will
  destroy all sub-interpreters that haven't been explicitly destroyed
  at that point.
\end{cfuncdesc}

\begin{cfuncdesc}{void}{Py_SetProgramName}{char *name}
  This function should be called before
  \cfunction{Py_Initialize()}\ttindex{Py_Initialize()} is called
  for the first time, if it is called at all.  It tells the
  interpreter the value of the \code{argv[0]} argument to the
  \cfunction{main()}\ttindex{main()} function of the program.  This is
  used by \cfunction{Py_GetPath()}\ttindex{Py_GetPath()} and some
  other functions below to find the Python run-time libraries relative
  to the interpreter executable.  The default value is
  \code{'python'}.  The argument should point to a zero-terminated
  character string in static storage whose contents will not change
  for the duration of the program's execution.  No code in the Python
  interpreter will change the contents of this storage.
\end{cfuncdesc}

\begin{cfuncdesc}{char*}{Py_GetProgramName}{}
  Return the program name set with
  \cfunction{Py_SetProgramName()}\ttindex{Py_SetProgramName()}, or the
  default.  The returned string points into static storage; the caller
  should not modify its value.
\end{cfuncdesc}

\begin{cfuncdesc}{char*}{Py_GetPrefix}{}
  Return the \emph{prefix} for installed platform-independent files.
  This is derived through a number of complicated rules from the
  program name set with \cfunction{Py_SetProgramName()} and some
  environment variables; for example, if the program name is
  \code{'/usr/local/bin/python'}, the prefix is \code{'/usr/local'}.
  The returned string points into static storage; the caller should
  not modify its value.  This corresponds to the \makevar{prefix}
  variable in the top-level \file{Makefile} and the
  \longprogramopt{prefix} argument to the \program{configure} script
  at build time.  The value is available to Python code as
  \code{sys.prefix}.  It is only useful on \UNIX{}.  See also the next
  function.
\end{cfuncdesc}

\begin{cfuncdesc}{char*}{Py_GetExecPrefix}{}
  Return the \emph{exec-prefix} for installed
  platform-\emph{de}pendent files.  This is derived through a number
  of complicated rules from the program name set with
  \cfunction{Py_SetProgramName()} and some environment variables; for
  example, if the program name is \code{'/usr/local/bin/python'}, the
  exec-prefix is \code{'/usr/local'}.  The returned string points into
  static storage; the caller should not modify its value.  This
  corresponds to the \makevar{exec_prefix} variable in the top-level
  \file{Makefile} and the \longprogramopt{exec-prefix} argument to the
  \program{configure} script at build  time.  The value is available
  to Python code as \code{sys.exec_prefix}.  It is only useful on
  \UNIX.

  Background: The exec-prefix differs from the prefix when platform
  dependent files (such as executables and shared libraries) are
  installed in a different directory tree.  In a typical installation,
  platform dependent files may be installed in the
  \file{/usr/local/plat} subtree while platform independent may be
  installed in \file{/usr/local}.

  Generally speaking, a platform is a combination of hardware and
  software families, e.g.  Sparc machines running the Solaris 2.x
  operating system are considered the same platform, but Intel
  machines running Solaris 2.x are another platform, and Intel
  machines running Linux are yet another platform.  Different major
  revisions of the same operating system generally also form different
  platforms.  Non-\UNIX{} operating systems are a different story; the
  installation strategies on those systems are so different that the
  prefix and exec-prefix are meaningless, and set to the empty string.
  Note that compiled Python bytecode files are platform independent
  (but not independent from the Python version by which they were
  compiled!).

  System administrators will know how to configure the \program{mount}
  or \program{automount} programs to share \file{/usr/local} between
  platforms while having \file{/usr/local/plat} be a different
  filesystem for each platform.
\end{cfuncdesc}

\begin{cfuncdesc}{char*}{Py_GetProgramFullPath}{}
  Return the full program name of the Python executable; this is 
  computed as a side-effect of deriving the default module search path 
  from the program name (set by
  \cfunction{Py_SetProgramName()}\ttindex{Py_SetProgramName()} above).
  The returned string points into static storage; the caller should
  not modify its value.  The value is available to Python code as
  \code{sys.executable}.
  \withsubitem{(in module sys)}{\ttindex{executable}}
\end{cfuncdesc}

\begin{cfuncdesc}{char*}{Py_GetPath}{}
  \indexiii{module}{search}{path}
  Return the default module search path; this is computed from the 
  program name (set by \cfunction{Py_SetProgramName()} above) and some
  environment variables.  The returned string consists of a series of
  directory names separated by a platform dependent delimiter
  character.  The delimiter character is \character{:} on \UNIX and Mac OS X,
  \character{;} on Windows.  The returned string points into
  static storage; the caller should not modify its value.  The value
  is available to Python code as the list
  \code{sys.path}\withsubitem{(in module sys)}{\ttindex{path}}, which
  may be modified to change the future search path for loaded
  modules.

  % XXX should give the exact rules
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetVersion}{}
  Return the version of this Python interpreter.  This is a string
  that looks something like

\begin{verbatim}
"1.5 (#67, Dec 31 1997, 22:34:28) [GCC 2.7.2.2]"
\end{verbatim}

  The first word (up to the first space character) is the current
  Python version; the first three characters are the major and minor
  version separated by a period.  The returned string points into
  static storage; the caller should not modify its value.  The value
  is available to Python code as \code{sys.version}.
  \withsubitem{(in module sys)}{\ttindex{version}}
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetBuildNumber}{}
  Return a string representing the Subversion revision that this Python
  executable was built from.  This number is a string because it may contain a
  trailing 'M' if Python was built from a mixed revision source tree.
  \versionadded{2.5}
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetPlatform}{}
  Return the platform identifier for the current platform.  On \UNIX,
  this is formed from the ``official'' name of the operating system,
  converted to lower case, followed by the major revision number;
  e.g., for Solaris 2.x, which is also known as SunOS 5.x, the value
  is \code{'sunos5'}.  On Mac OS X, it is \code{'darwin'}.  On Windows,
  it is \code{'win'}.  The returned string points into static storage;
  the caller should not modify its value.  The value is available to
  Python code as \code{sys.platform}.
  \withsubitem{(in module sys)}{\ttindex{platform}}
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetCopyright}{}
  Return the official copyright string for the current Python version,
  for example

  \code{'Copyright 1991-1995 Stichting Mathematisch Centrum, Amsterdam'}

  The returned string points into static storage; the caller should
  not modify its value.  The value is available to Python code as
  \code{sys.copyright}.
  \withsubitem{(in module sys)}{\ttindex{copyright}}
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetCompiler}{}
  Return an indication of the compiler used to build the current
  Python version, in square brackets, for example:

\begin{verbatim}
"[GCC 2.7.2.2]"
\end{verbatim}

  The returned string points into static storage; the caller should
  not modify its value.  The value is available to Python code as part
  of the variable \code{sys.version}.
  \withsubitem{(in module sys)}{\ttindex{version}}
\end{cfuncdesc}

\begin{cfuncdesc}{const char*}{Py_GetBuildInfo}{}
  Return information about the sequence number and build date and time 
  of the current Python interpreter instance, for example

\begin{verbatim}
"#67, Aug  1 1997, 22:34:28"
\end{verbatim}

  The returned string points into static storage; the caller should
  not modify its value.  The value is available to Python code as part