From db65a6ce556b1e311d03837fbf85ca52ef2c5d07 Mon Sep 17 00:00:00 2001 From: Guido van Rossum Date: Fri, 5 Nov 1993 17:11:16 +0000 Subject: * ext.tex: did most of the tedious changes from plain ASCII text to LaTeX. * text2latex.py: automatically put function names in \code{}. * lib.tex, ref.tex, ext.tex, qua.tex, tut.tex: use new P.O.Box number in address. --- Doc/ext.tex | 574 +++++++++++++++++++++++++----------------------- Doc/ext/ext.tex | 574 +++++++++++++++++++++++++----------------------- Doc/lib.tex | 4 +- Doc/lib/lib.tex | 4 +- Doc/qua.tex | 4 +- Doc/ref.tex | 4 +- Doc/ref/ref.tex | 4 +- Doc/text2latex.py | 7 + Doc/tools/text2latex.py | 7 + Doc/tut.tex | 4 +- Doc/tut/tut.tex | 4 +- 11 files changed, 632 insertions(+), 558 deletions(-) diff --git a/Doc/ext.tex b/Doc/ext.tex index 68aece0..cfdf8be 100644 --- a/Doc/ext.tex +++ b/Doc/ext.tex @@ -1,11 +1,11 @@ -\documentstyle[twoside,11pt,myformat]{report} +\documentstyle[twoside,11pt,myformat,times]{report} \title{\bf Extending and Embedding the Python Interpreter} \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } @@ -39,12 +39,13 @@ interpreter as a library package from applications using Python as an \pagenumbering{arabic} + \chapter{Extending Python with C or C++ code} It is quite easy to add non-standard built-in modules to Python, if you know how to program in C. A built-in module known to the Python -programmer as foo is generally implemented in a file called -foomodule.c. The standard built-in modules also adhere to this +programmer as \code{foo} is generally implemented in a file called +\file{foomodule.c}. The standard built-in modules also adhere to this convention, and in fact some of them form excellent examples of how to create an extension. @@ -53,11 +54,12 @@ Python: implement new data types and provide access to system calls or C library functions. Since the latter is usually the most important reason for adding an extension, I'll concentrate on adding "wrappers" around C library functions; the concrete example uses the wrapper for -system() in module posix, found in (of course) the file posixmodule.c. +\code{system()} in module posix, found in (of course) the file +posixmodule.c. It is important not to be impressed by the size and complexity of the average extension module; much of this is straightforward -"boilerplate" code (starting right with the copyright notice!). +``boilerplate'' code (starting right with the copyright notice!). Let's skip the boilerplate and jump right to an interesting function: @@ -100,20 +102,20 @@ otherwise the Python user could cause a core dump by passing the wrong arguments (or no arguments at all). Because argument checking and converting arguments to C is such a common task, there's a general function in the Python interpreter which combines these tasks: -getargs(). It uses a template string to determine both the types of -the Python argument and the types of the C variables into which it -should store the converted values. +\code{getargs()}. It uses a template string to determine both the +types of the Python argument and the types of the C variables into +which it should store the converted values. When getargs returns nonzero, the argument list has the right type and its components have been stored in the variables whose addresses are passed. When it returns zero, an error has occurred. In the latter case it has already raised an appropriate exception by calling -err_setstr(), so the calling function can just return NULL. +\code{err_setstr()}, so the calling function can just return NULL. The form of the format string is described at the end of this file. -(There are convenience macros getstrarg(), getintarg(), etc., for many -common forms of argument lists. These are relics from the past; it's -better to call getargs() directly.) +(There are convenience macros \code{getstrarg()}, \code{getintarg()}, +etc., for many common forms of argument lists. These are relics from +the past; it's better to call \code{getargs()} directly.) \section{Intermezzo: errors and exceptions} @@ -122,56 +124,58 @@ An important convention throughout the Python interpreter is the following: when a function fails, it should set an exception condition and return an error value (often a NULL pointer). Exceptions are set in a global variable in the file errors.c; if this variable is NULL no -exception has occurred. A second variable is the "associated value" +exception has occurred. A second variable is the ``associated value'' of the exception. The file errors.h declares a host of err_* functions to set various -types of exceptions. The most common one is err_setstr() -- its -arguments are an exception object (e.g. RuntimeError -- actually it +types of exceptions. The most common one is \code{err_setstr()} --- its +arguments are an exception object (e.g. RuntimeError --- actually it can be any string object) and a C string indicating the cause of the error (this is converted to a string object and stored as the -"associated value" of the exception). Another useful function is -err_errno(), which only takes an exception argument and constructs the -associated value by inspection of the (UNIX) global variable errno. +``associated value'' of the exception). Another useful function is +\code{err_errno()}, which only takes an exception argument and +constructs the associated value by inspection of the (UNIX) global +variable errno. You can test non-destructively whether an exception has been set with -err_occurred(). However, most code never calls err_occurred() to see -whether an error occurred or not, but relies on error return values -from the functions it calls instead: +\code{err_occurred()}. However, most code never calls +\code{err_occurred()} to see whether an error occurred or not, but +relies on error return values from the functions it calls instead: When a function that calls another function detects that the called function fails, it should return an error value but not set an -condition -- one is already set. The caller is then supposed to also +condition --- one is already set. The caller is then supposed to also return an error indication to *its* caller, again *without* calling -err_setstr(), and so on -- the most detailed cause of the error was -already reported by the function that detected it in the first place. -Once the error has reached Python's interpreter main loop, this aborts -the currently executing Python code and tries to find an exception -handler specified by the Python programmer. +\code{err_setstr()}, and so on --- the most detailed cause of the error +was already reported by the function that detected it in the first +place. Once the error has reached Python's interpreter main loop, +this aborts the currently executing Python code and tries to find an +exception handler specified by the Python programmer. To ignore an exception set by a function call that failed, the -exception condition must be cleared explicitly by calling err_clear(). -The only time C code should call err_clear() is if it doesn't want to -pass the error on to the interpreter but wants to handle it completely -by itself (e.g. by trying something else or pretending nothing -happened). +exception condition must be cleared explicitly by calling +\code{err_clear()}. The only time C code should call +\code{err_clear()} is if it doesn't want to pass the error on to the +interpreter but wants to handle it completely by itself (e.g. by +trying something else or pretending nothing happened). -Finally, the function err_get() gives you both error variables +Finally, the function \code{err_get()} gives you both error variables *and clears them*. Note that even if an error occurred the second one may be NULL. I doubt you will need to use this function. -Note that a failing malloc() call must also be turned into an -exception -- the direct caller of malloc() (or realloc()) must call -err_nomem() and return a failure indicator itself. All the -object-creating functions (newintobject() etc.) already do this, so -only if you call malloc() directly this note is of importance. +Note that a failing \code{malloc()} call must also be turned into an +exception --- the direct caller of \code{malloc()} (or +\code{realloc()}) must call \code{err_nomem()} and return a failure +indicator itself. All the object-creating functions +(\code{newintobject()} etc.) already do this, so only if you call +\code{malloc()} directly this note is of importance. -Also note that, with the important exception of getargs(), functions +Also note that, with the important exception of \code{getargs()}, functions that return an integer status usually use 0 for success and -1 for failure. Finally, be careful about cleaning up garbage (making appropriate -[X]DECREF() calls) when you return an error! +[\code{X}]\code{DECREF()} calls) when you return an error! \section{Back to the example} @@ -186,7 +190,7 @@ bit: It returns NULL (the error indicator for functions of this kind) if an error is detected in the argument list, relying on the exception set -by getargs(). The string value of the argument is now copied to the +by \code{getargs()}. The string value of the argument is now copied to the local variable 'command'. If a Python function is called with multiple arguments, the argument @@ -195,18 +199,18 @@ instance, to explicitly create the tuple containing the arguments first and make the call later. The next statement in posix_system is a call tothe C library function -system(), passing it the string we just got from getargs(): +\code{system()}, passing it the string we just got from \code{getargs()}: \begin{verbatim} sts = system(command); \end{verbatim} Python strings may contain internal null bytes; but if these occur in -this example the rest of the string will be ignored by system(). +this example the rest of the string will be ignored by \code{system()}. -Finally, posix.system() must return a value: the integer status -returned by the C library system() function. This is done by the -function newintobject(), which takes a (long) integer as parameter. +Finally, posix.\code{system()} must return a value: the integer status +returned by the C library \code{system()} function. This is done by the +function \code{newintobject()}, which takes a (long) integer as parameter. \begin{verbatim} return newintobject((long)sts); @@ -223,13 +227,13 @@ this idiom: 'None' is a unique Python object representing 'no value'. It differs from NULL, which means 'error' in most contexts (except when passed as -a function argument -- there it means 'no arguments'). +a function argument --- there it means 'no arguments'). \section{The module's function table} -I promised to show how I made the function posix_system() available to -Python programs. This is shown later in posixmodule.c: +I promised to show how I made the function \code{posix_system()} +available to Python programs. This is shown later in posixmodule.c: \begin{verbatim} static struct methodlist posix_methods[] = { @@ -246,27 +250,27 @@ Python programs. This is shown later in posixmodule.c: } \end{verbatim} -(The actual initposix() is somewhat more complicated, but most +(The actual \code{initposix()} is somewhat more complicated, but most extension modules are indeed as simple as that.) When the Python -program first imports module 'posix', initposix() is called, which -calls initmodule() with specific parameters. This creates a module -object (which is inserted in the table sys.modules under the key -'posix'), and adds built-in-function objects to the newly created -module based upon the table (of type struct methodlist) that was -passed as its second parameter. The function initmodule() returns a -pointer to the module object that it creates, but this is unused here. -It aborts with a fatal error if the module could not be initialized -satisfactorily. +program first imports module 'posix', \code{initposix()} is called, +which calls \code{initmodule()} with specific parameters. This +creates a module object (which is inserted in the table sys.modules +under the key 'posix'), and adds built-in-function objects to the +newly created module based upon the table (of type struct methodlist) +that was passed as its second parameter. The function +\code{initmodule()} returns a pointer to the module object that it +creates, but this is unused here. It aborts with a fatal error if the +module could not be initialized satisfactorily. \section{Calling the module initialization function} There is one more thing to do: telling the Python module to call the -initfoo() function when it encounters an 'import foo' statement. +\code{initfoo()} function when it encounters an 'import foo' statement. This is done in the file config.c. This file contains a table mapping module names to parameterless void function pointers. You need to add -a declaration of initfoo() somewhere early in the file, and a line -saying +a declaration of \code{initfoo()} somewhere early in the file, and a +line saying \begin{verbatim} {"foo", initfoo}, @@ -274,12 +278,12 @@ saying to the initializer for inittab[]. It is conventional to include both the declaration and the initializer line in preprocessor commands -\verb\#ifdef USE_FOO\ / \verb\#endif\, to make it easy to turn the foo -extension on or off. Note that the Macintosh version uses a different -configuration file, distributed as configmac.c. This strategy may be -extended to other operating system versions, although usually the -standard config.c file gives a pretty useful starting point for a new -config*.c file. +\code{\#ifdef USE_FOO} / \code{\#endif}, to make it easy to turn the +foo extension on or off. Note that the Macintosh version uses a +different configuration file, distributed as configmac.c. This +strategy may be extended to other operating system versions, although +usually the standard config.c file gives a pretty useful starting +point for a new config*.c file. And, of course, I forgot the Makefile. This is actually not too hard, just follow the examples for, say, AMOEBA. Just find all occurrences @@ -287,8 +291,8 @@ of the string AMOEBA in the Makefile and do the same for FOO that's done for AMOEBA... (Note: if you are using dynamic loading for your extension, you don't -need to edit config.c and the Makefile. See "./DYNLOAD" for more info -about this.) +need to edit config.c and the Makefile. See \file{./DYNLOAD} for more +info about this.) \section{Calling Python functions from C} @@ -296,7 +300,7 @@ about this.) The above concentrates on making C functions accessible to the Python programmer. The reverse is also often useful: calling Python functions from C. This is especially the case for libraries that -support so-called "callback" functions. If a C interface makes heavy +support so-called ``callback'' functions. If a C interface makes heavy use of callbacks, the equivalent Python often needs to provide a callback mechanism to the Python programmer; the implementation may require calling the Python callback functions from a C callback. @@ -305,14 +309,14 @@ Other uses are also possible. Fortunately, the Python interpreter is easily called recursively, and there is a standard interface to call a Python function. I won't dwell on how to call the Python parser with a particular string as -input -- if you're interested, have a look at the implementation of -the "-c" command line option in pythonmain.c. +input --- if you're interested, have a look at the implementation of +the \samp{-c} command line option in pythonmain.c. Calling a Python function is easy. First, the Python program must somehow pass you the Python function object. You should provide a function (or some other interface) to do this. When this function is called, save a pointer to the Python function object (be careful to -INCREF it!) in a global variable -- or whereever you see fit. +INCREF it!) in a global variable --- or whereever you see fit. For example, the following function might be part of a module definition: @@ -333,9 +337,9 @@ definition: \end{verbatim} Later, when it is time to call the function, you call the C function -call_object(). This function has two arguments, both pointers to -arbitrary Python objects: the Python function, and the argument. The -argument can be NULL to call the function without arguments. For +\code{call_object()}. This function has two arguments, both pointers +to arbitrary Python objects: the Python function, and the argument. +The argument can be NULL to call the function without arguments. For example: \begin{verbatim} @@ -345,21 +349,22 @@ example: result = call_object(my_callback, (object *)NULL); \end{verbatim} -call_object() returns a Python object pointer: this is -the return value of the Python function. call_object() is -"reference-count-neutral" with respect to its arguments, but the -return value is "new": either it is a brand new object, or it is an +\code{call_object()} returns a Python object pointer: this is +the return value of the Python function. \code{call_object()} is +``reference-count-neutral'' with respect to its arguments, but the +return value is ``new'': either it is a brand new object, or it is an existing object whose reference count has been incremented. So, you should somehow apply DECREF to the result, even (especially!) if you are not interested in its value. Before you do this, however, it is important to check that the return value isn't NULL. If it is, the Python function terminated by raising -an exception. If the C code that called call_object() is called from -Python, it should now return an error indication to its Python caller, -so the interpreter can print a stack trace, or the calling Python code -can handle the exception. If this is not possible or desirable, the -exception should be cleared by calling err_clear(). For example: +an exception. If the C code that called \code{call_object()} is +called from Python, it should now return an error indication to its +Python caller, so the interpreter can print a stack trace, or the +calling Python code can handle the exception. If this is not possible +or desirable, the exception should be cleared by calling +\code{err_clear()}. For example: \begin{verbatim} if (result == NULL) @@ -369,13 +374,14 @@ exception should be cleared by calling err_clear(). For example: \end{verbatim} Depending on the desired interface to the Python callback function, -you may also have to provide an argument to call_object(). In some -cases the argument is also provided by the Python program, through the -same interface that specified the callback function. It can then be -saved and used in the same manner as the function object. In other -cases, you may have to construct a new object to pass as argument. In -this case you must dispose of it as well. For example, if you want to -pass an integral event code, you might use the following code: +you may also have to provide an argument to \code{call_object()}. In +some cases the argument is also provided by the Python program, +through the same interface that specified the callback function. It +can then be saved and used in the same manner as the function object. +In other cases, you may have to construct a new object to pass as +argument. In this case you must dispose of it as well. For example, +if you want to pass an integral event code, you might use the +following code: \begin{verbatim} object *argument; @@ -391,8 +397,8 @@ pass an integral event code, you might use the following code: Note the placement of DECREF(argument) immediately after the call, before the error check! Also note that strictly spoken this code is -not complete: newintobject() may run out of memory, and this should be -checked. +not complete: \code{newintobject()} may run out of memory, and this +should be checked. In even more complicated cases you may want to pass the callback function multiple arguments. To this end you have to construct (and @@ -401,13 +407,15 @@ errror checks and reference count manipulation) are left as an exercise for the reader; most of this is also needed when returning multiple values from a function. -XXX TO DO: explain objects and reference counting. +XXX TO DO: explain objects. + XXX TO DO: defining new object types. -\section{Format strings for getargs()} +\section{Format strings for {\tt getargs()}} -The getargs() function is declared in "modsupport.h" as follows: +The \code{getargs()} function is declared in \file{modsupport.h} as +follows: \begin{verbatim} int getargs(object *arg, char *format, ...); @@ -416,89 +424,85 @@ The getargs() function is declared in "modsupport.h" as follows: The remaining arguments must be addresses of variables whose type is determined by the format string. For the conversion to succeed, the `arg' object must match the format and the format must be exhausted. -Note that while getargs() checks that the Python object really is of -the specified type, it cannot check that the addresses provided in the -call match: if you make mistakes there, your code will probably dump -core. +Note that while \code{getargs()} checks that the Python object really +is of the specified type, it cannot check that the addresses provided +in the call match: if you make mistakes there, your code will probably +dump core. A format string consists of a single `format unit'. A format unit describes one Python object; it is usually a single character or a parenthesized string. The type of a format units is determined from its first character, the `format letter': -'s' (string) - The Python object must be a string object. The C argument - must be a char** (i.e., the address of a character pointer), - and a pointer to the C string contained in the Python object - is stored into it. If the next character in the format string - is \verb\'#'\, another C argument of type int* must be present, and - the length of the Python string (not counting the trailing - zero byte) is stored into it. - -'z' (string or zero, i.e., NULL) - Like 's', but the object may also be None. In this case the - string pointer is set to NULL and if a \verb\'#'\ is present the size - it set to 0. - -'b' (byte, i.e., char interpreted as tiny int) - The object must be a Python integer. The C argument must be a - char*. - -'h' (half, i.e., short) - The object must be a Python integer. The C argument must be a - short*. - -'i' (int) - The object must be a Python integer. The C argument must be - an int*. - -'l' (long) - The object must be a (plain!) Python integer. The C argument - must be a long*. - -'c' (char) - The Python object must be a string of length 1. The C - argument must be a char*. (Don't pass an int*!) - -'f' (float) - The object must be a Python int or float. The C argument must - be a float*. - -'d' (double) - The object must be a Python int or float. The C argument must - be a double*. - -'S' (string object) - The object must be a Python string. The C argument must be an - object** (i.e., the address of an object pointer). The C - program thus gets back the actual string object that was - passed, not just a pointer to its array of characters and its - size as for format character 's'. - -'O' (object) - The object can be any Python object, including None, but not - NULL. The C argument must be an object**. This can be used - if an argument list must contain objects of a type for which - no format letter exist: the caller must then check that it has - the right type. - -'(' (tuple) - The object must be a Python tuple. Following the '(' - character in the format string must come a number of format - units describing the elements of the tuple, followed by a ')' - character. Tuple format units may be nested. (There are no - exceptions for empty and singleton tuples; "()" specifies an - empty tuple and "(i)" a singleton of one integer. Normally - you don't want to use the latter, since it is hard for the - user to specify. - +\begin{description} + +\item[\samp{s} (string)] +The Python object must be a string object. The C argument must be a +char** (i.e. the address of a character pointer), and a pointer to +the C string contained in the Python object is stored into it. If the +next character in the format string is \samp{\#}, another C argument +of type int* must be present, and the length of the Python string (not +counting the trailing zero byte) is stored into it. + +\item[\samp{z} (string or zero, i.e. \code{NULL})] +Like \samp{s}, but the object may also be None. In this case the +string pointer is set to NULL and if a \samp{\#} is present the size +it set to 0. + +\item[\samp{b} (byte, i.e. char interpreted as tiny int)] +The object must be a Python integer. The C argument must be a char*. + +\item[\samp{h} (half, i.e. short)] +The object must be a Python integer. The C argument must be a short*. + +\item[\samp{i} (int)] +The object must be a Python integer. The C argument must be an int*. + +\item[\samp{l} (long)] +The object must be a (plain!) Python integer. The C argument must be +a long*. + +\item[\samp{c} (char)] +The Python object must be a string of length 1. The C argument must +be a char*. (Don't pass an int*!) + +\item[\samp{f} (float)] +The object must be a Python int or float. The C argument must be a +float*. + +\item[\samp{d} (double)] +The object must be a Python int or float. The C argument must be a +double*. + +\item[\samp{S} (string object)] +The object must be a Python string. The C argument must be an +object** (i.e. the address of an object pointer). The C program thus +gets back the actual string object that was passed, not just a pointer +to its array of characters and its size as for format character +\samp{s}. + +\item[\samp{O} (object)] +The object can be any Python object, including None, but not NULL. +The C argument must be an object**. This can be used if an argument +list must contain objects of a type for which no format letter exist: +the caller must then check that it has the right type. + +\item[\samp{(} (tuple)] +The object must be a Python tuple. Following the \samp{(} character +in the format string must come a number of format units describing the +elements of the tuple, followed by a \samp{)} character. Tuple +format units may be nested. (There are no exceptions for empty and +singleton tuples; \samp{()} specifies an empty tuple and \samp{(i)} a +singleton of one integer. Normally you don't want to use the latter, +since it is hard for the user to specify. + +\end{description} More format characters will probably be added as the need arises. It should be allowed to use Python long integers whereever integers are expected, and perform a range check. (A range check is in fact always -necessary for the 'b', 'h' and 'i' format letters, but this is -currently not implemented.) - +necessary for the \samp{b}, \samp{h} and \samp{i} format +letters, but this is currently not implemented.) Some example calls: @@ -533,14 +537,14 @@ Some example calls: \end{verbatim} Note that a format string must consist of a single unit; strings like -\verb\'is'\ and \verb\'(ii)s#'\ are not valid format strings. (But -\verb\'s#'\ is.) +\samp{is} and \samp{(ii)s\#} are not valid format strings. (But +\samp{s\#} is.) - -The getargs() function does not support variable-length argument -lists. In simple cases you can fake these by trying several calls to -getargs() until one succeeds, but you must take care to call -err_clear() before each retry. For example: +The \code{getargs()} function does not support variable-length +argument lists. In simple cases you can fake these by trying several +calls to +\code{getargs()} until one succeeds, but you must take care to call +\code{err_clear()} before each retry. For example: \begin{verbatim} static object *my_method(self, args) object *self, *args; { @@ -561,46 +565,47 @@ err_clear() before each retry. For example: \end{verbatim} (It is possible to think of an extension to the definition of format -strings to accomodate this directly, e.g., placing a '|' in a tuple -might specify that the remaining arguments are optional. getargs() -should then return 1 + the number of variables stored into.) - +strings to accomodate this directly, e.g., placing a \samp{|} in a +tuple might specify that the remaining arguments are optional. +\code{getargs()} should then return one more than the number of +variables stored into.) Advanced users note: If you set the `varargs' flag in the method list for a function, the argument will always be a tuple (the `raw argument list'). In this case you must enclose single and empty argument lists -in parentheses, e.g., "(s)" and "()". +in parentheses, e.g., \samp{(s)} and \samp{()}. -\section{The mkvalue() function} +\section{The {\tt mkvalue()} function} -This function is the counterpart to getargs(). It is declared in -"modsupport.h" as follows: +This function is the counterpart to \code{getargs()}. It is declared +in \file{modsupport.h} as follows: \begin{verbatim} object *mkvalue(char *format, ...); \end{verbatim} -It supports exactly the same format letters as getargs(), but the -arguments (which are input to the function, not output) must not be -pointers, just values. If a byte, short or float is passed to a +It supports exactly the same format letters as \code{getargs()}, but +the arguments (which are input to the function, not output) must not +be pointers, just values. If a byte, short or float is passed to a varargs function, it is widened by the compiler to int or double, so -'b' and 'h' are treated as 'i' and 'f' is treated as 'd'. 'S' is -treated as 'O', 's' is treated as 'z'. \verb\'z#'\ and \verb\'s#'\ -are supported: a second argument specifies the length of the data -(negative means use strlen()). 'S' and 'O' add a reference to their -argument (so you should DECREF it if you've just created it and aren't -going to use it again). - -If the argument for 'O' or 'S' 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, mkvalue() will return NULL but won't -set an exception if one is already set. If no exception is set, -SystemError is set. - -If there is an error in the format string, the SystemError exception -is set, since it is the calling C code's fault, not that of the Python -user who sees the exception. +\samp{b} and \samp{h} are treated as \samp{i} and \samp{f} is +treated as \samp{d}. \samp{S} is treated as \samp{O}, \samp{s} is +treated as \samp{z}. \samp{z\#} and \samp{s\#} are supported: a +second argument specifies the length of the data (negative means use +\code{strlen()}). \samp{S} and \samp{O} add a reference to their +argument (so you should \code{DECREF()} it if you've just created it +and aren't going to use it again). + +If the argument for \samp{O} or \samp{S} 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, \code{mkvalue()} will +return \code{NULL} but won't set an exception if one is already set. +If no exception is set, \code{SystemError} is set. + +If there is an error in the format string, the \code{SystemError} +exception is set, since it is the calling C code's fault, not that of +the Python user who sees the exception. Example: @@ -610,99 +615,124 @@ Example: returns a tuple containing two zeros. (Outer parentheses in the format string are actually superfluous, but you can use them for -compatibility with getargs(), which requires them if more than one -argument is expected.) +compatibility with \code{getargs()}, which requires them if more than +one argument is expected.) + \section{Reference counts} -Here's a useful explanation of INCREF and DECREF by Sjoerd Mullender. +Here's a useful explanation of \code{INCREF()} and \code{DECREF()} +(after an original by Sjoerd Mullender). -Use XINCREF or XDECREF instead of INCREF/DECREF when the argument may -be NULL. +Use \code{XINCREF()} or \code{XDECREF()} instead of \code{INCREF()} / +\code{DECREF()} when the argument may be \code{NULL}. The basic idea is, if you create an extra reference to an object, you -must INCREF it, if you throw away a reference to an object, you must -DECREF it. Functions such as newstringobject, newsizedstringobject, -newintobject, etc. create a reference to an object. If you want to -throw away the object thus created, you must use DECREF. - -If you put an object into a tuple, list, or dictionary, the idea is -that you usually don't want to keep a reference of your own around, so -Python does not INCREF the elements. It does DECREF the old value. +must \code{INCREF()} it, if you throw away a reference to an object, +you must \code{DECREF()} it. Functions such as +\code{newstringobject()}, \code{newsizedstringobject()}, +\code{newintobject()}, etc. create a reference to an object. If you +want to throw away the object thus created, you must use +\code{DECREF()}. + +If you put an object into a tuple or list using \code{settupleitem()} +or \code{setlistitem()}, the idea is that you usually don't want to +keep a reference of your own around, so Python does not +\code{INCREF()} the elements. It does \code{DECREF()} the old value. This means that if you put something into such an object using the -functions Python provides for this, you must INCREF the object if you -want to keep a separate reference to the object around. Also, if you -replace an element, you should INCREF the old element first if you -want to keep it. If you didn't INCREF it before you replaced it, you -are not allowed to look at it anymore, since it may have been freed. - -Returning an object to Python (i.e., when your module function -returns) creates a reference to an object, but it does not change the -reference count. When your module does not keep another reference to -the object, you should not INCREF or DECREF it. When you do keep a -reference around, you should INCREF the object. Also, when you return -a global object such as None, you should INCREF it. - -If you want to return a tuple, you should consider using mkvalue. -Mkvalue creates a new tuple with a reference count of 1 which you can -return. If any of the elements you put into the tuple are objects, -they are INCREFfed by mkvalue. If you don't want to keep references -to those elements around, you should DECREF them after having called -mkvalue. - -Usually you don't have to worry about arguments. They are INCREFfed -before your function is called and DECREFfed after your function -returns. When you keep a reference to an argument, you should INCREF -it and DECREF when you throw it away. Also, when you return an -argument, you should INCREF it, because returning the argument creates -an extra reference to it. - -If you use getargs() to parse the arguments, you can get a reference -to an object (by using "O" in the format string). This object was not -INCREFfed, so you should not DECREF it. If you want to keep the -object, you must INCREF it yourself. - -If you create your own type of objects, you should use NEWOBJ to -create the object. This sets the reference count to 1. If you want -to throw away the object, you should use DECREF. When the reference -count reaches 0, the dealloc function is called. In it, you should -DECREF all object to which you keep references in your object, but you -should not use DECREF on your object. You should use DEL instead. +functions Python provides for this, you must \code{INCREF()} the +object if you also want to keep a separate reference to the object around. +Also, if you replace an element, you should \code{INCREF()} the old +element first if you want to keep it. If you didn't \code{INCREF()} +it before you replaced it, you are not allowed to look at it anymore, +since it may have been freed. + +Returning an object to Python (i.e. when your C function returns) +creates a reference to an object, but it does not change the reference +count. When your code does not keep another reference to the object, +you should not \code{INCREF()} or \code{DECREF()} it (assuming it is a +newly created object). When you do keep a reference around, you +should \code{INCREF()} the object. Also, when you return a global +object such as \code{None}, you should \code{INCREF()} it. + +If you want to return a tuple, you should consider using +\code{mkvalue()}. This function creates a new tuple with a reference +count of 1 which you can return. If any of the elements you put into +the tuple are objects (format codes \samp{O} or \samp{S}), they +are \code{INCREF()}'ed by \code{mkvalue()}. If you don't want to keep +references to those elements around, you should \code{DECREF()} them +after having called \code{mkvalue()}. + +Usually you don't have to worry about arguments. They are +\code{INCREF()}'ed before your function is called and +\code{DECREF()}'ed after your function returns. When you keep a +reference to an argument, you should \code{INCREF()} it and +\code{DECREF()} when you throw it away. Also, when you return an +argument, you should \code{INCREF()} it, because returning the +argument creates an extra reference to it. + +If you use \code{getargs()} to parse the arguments, you can get a +reference to an object (by using \samp{O} in the format string). This +object was not \code{INCREF()}'ed, so you should not \code{DECREF()} +it. If you want to keep the object, you must \code{INCREF()} it +yourself. + +If you create your own type of objects, you should use \code{NEWOBJ()} +to create the object. This sets the reference count to 1. If you +want to throw away the object, you should use \code{DECREF()}. When +the reference count reaches zero, your type's \code{dealloc()} +function is called. In it, you should \code{DECREF()} all object to +which you keep references in your object, but you should not use +\code{DECREF()} on your object. You should use \code{DEL()} instead. + + +\section{Using C++} + +It is possible to write extension modules in C++. Some restrictions +apply: since the main program (the Python interpreter) is compiled and +linked by the C compiler, global or static objects with constructors +cannot be used. All functions that will be called directly or +indirectly (i.e. via function pointers) by the Python interpreter will +have to be declared using \code{extern "C"}; this applies to all +`methods' as well as to the module's initialization function. +It is unnecessary to enclose the Python header files in +\code{extern "C" \{...\}} --- they do this already. + \chapter{Embedding Python in another application} Embedding Python is similar to extending it, but not quite. The difference is that when you extend Python, the main program of the application is still the Python interpreter, while of you embed -Python, the main program may have nothing to do with Python -- +Python, the main program may have nothing to do with Python --- instead, some parts of the application occasionally call the Python interpreter to run some Python code. So if you are embedding Python, you are providing your own main program. One of the things this main program has to do is initialize the Python interpreter. At the very least, you have to call the -function initall(). There are optional calls to pass command line -arguments to Python. Then later you can call the interpreter from any -part of the application. +function \code{initall()}. There are optional calls to pass command +line arguments to Python. Then later you can call the interpreter +from any part of the application. There are several different ways to call the interpreter: you can pass -a string containing Python statements to run_command(), or you can -pass a stdio file pointer and a file name (for identification in error -messages only) to run_script(). You can also call the lower-level -operations described (partly) in the file \verb\/misc/EXTENDING\ -to construct and use Python objects. +a string containing Python statements to \code{run_command()}, or you +can pass a stdio file pointer and a file name (for identification in +error messages only) to \code{run_script()}. You can also call the +lower-level operations described in the previous chapters to construct +and use Python objects. A simple demo of embedding Python can be found in the directory -\verb\/embed/\. +\file{/embed}. + \section{Using C++} It is also possible to embed Python in a C++ program; how this is done exactly will depend on the details of the C++ system used; in general -you will need to write the main program in C++, enclosing the include -files in \verb\"extern "C" { ... }"\, and compile and link this with -the C++ compiler. (There is no need to recompile Python itself with -C++.) +you will need to write the main program in C++, and use the C++ +compiler to compile and link your program. There is no need to +recompile Python itself with C++. \input{ext.ind} diff --git a/Doc/ext/ext.tex b/Doc/ext/ext.tex index 68aece0..cfdf8be 100644 --- a/Doc/ext/ext.tex +++ b/Doc/ext/ext.tex @@ -1,11 +1,11 @@ -\documentstyle[twoside,11pt,myformat]{report} +\documentstyle[twoside,11pt,myformat,times]{report} \title{\bf Extending and Embedding the Python Interpreter} \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } @@ -39,12 +39,13 @@ interpreter as a library package from applications using Python as an \pagenumbering{arabic} + \chapter{Extending Python with C or C++ code} It is quite easy to add non-standard built-in modules to Python, if you know how to program in C. A built-in module known to the Python -programmer as foo is generally implemented in a file called -foomodule.c. The standard built-in modules also adhere to this +programmer as \code{foo} is generally implemented in a file called +\file{foomodule.c}. The standard built-in modules also adhere to this convention, and in fact some of them form excellent examples of how to create an extension. @@ -53,11 +54,12 @@ Python: implement new data types and provide access to system calls or C library functions. Since the latter is usually the most important reason for adding an extension, I'll concentrate on adding "wrappers" around C library functions; the concrete example uses the wrapper for -system() in module posix, found in (of course) the file posixmodule.c. +\code{system()} in module posix, found in (of course) the file +posixmodule.c. It is important not to be impressed by the size and complexity of the average extension module; much of this is straightforward -"boilerplate" code (starting right with the copyright notice!). +``boilerplate'' code (starting right with the copyright notice!). Let's skip the boilerplate and jump right to an interesting function: @@ -100,20 +102,20 @@ otherwise the Python user could cause a core dump by passing the wrong arguments (or no arguments at all). Because argument checking and converting arguments to C is such a common task, there's a general function in the Python interpreter which combines these tasks: -getargs(). It uses a template string to determine both the types of -the Python argument and the types of the C variables into which it -should store the converted values. +\code{getargs()}. It uses a template string to determine both the +types of the Python argument and the types of the C variables into +which it should store the converted values. When getargs returns nonzero, the argument list has the right type and its components have been stored in the variables whose addresses are passed. When it returns zero, an error has occurred. In the latter case it has already raised an appropriate exception by calling -err_setstr(), so the calling function can just return NULL. +\code{err_setstr()}, so the calling function can just return NULL. The form of the format string is described at the end of this file. -(There are convenience macros getstrarg(), getintarg(), etc., for many -common forms of argument lists. These are relics from the past; it's -better to call getargs() directly.) +(There are convenience macros \code{getstrarg()}, \code{getintarg()}, +etc., for many common forms of argument lists. These are relics from +the past; it's better to call \code{getargs()} directly.) \section{Intermezzo: errors and exceptions} @@ -122,56 +124,58 @@ An important convention throughout the Python interpreter is the following: when a function fails, it should set an exception condition and return an error value (often a NULL pointer). Exceptions are set in a global variable in the file errors.c; if this variable is NULL no -exception has occurred. A second variable is the "associated value" +exception has occurred. A second variable is the ``associated value'' of the exception. The file errors.h declares a host of err_* functions to set various -types of exceptions. The most common one is err_setstr() -- its -arguments are an exception object (e.g. RuntimeError -- actually it +types of exceptions. The most common one is \code{err_setstr()} --- its +arguments are an exception object (e.g. RuntimeError --- actually it can be any string object) and a C string indicating the cause of the error (this is converted to a string object and stored as the -"associated value" of the exception). Another useful function is -err_errno(), which only takes an exception argument and constructs the -associated value by inspection of the (UNIX) global variable errno. +``associated value'' of the exception). Another useful function is +\code{err_errno()}, which only takes an exception argument and +constructs the associated value by inspection of the (UNIX) global +variable errno. You can test non-destructively whether an exception has been set with -err_occurred(). However, most code never calls err_occurred() to see -whether an error occurred or not, but relies on error return values -from the functions it calls instead: +\code{err_occurred()}. However, most code never calls +\code{err_occurred()} to see whether an error occurred or not, but +relies on error return values from the functions it calls instead: When a function that calls another function detects that the called function fails, it should return an error value but not set an -condition -- one is already set. The caller is then supposed to also +condition --- one is already set. The caller is then supposed to also return an error indication to *its* caller, again *without* calling -err_setstr(), and so on -- the most detailed cause of the error was -already reported by the function that detected it in the first place. -Once the error has reached Python's interpreter main loop, this aborts -the currently executing Python code and tries to find an exception -handler specified by the Python programmer. +\code{err_setstr()}, and so on --- the most detailed cause of the error +was already reported by the function that detected it in the first +place. Once the error has reached Python's interpreter main loop, +this aborts the currently executing Python code and tries to find an +exception handler specified by the Python programmer. To ignore an exception set by a function call that failed, the -exception condition must be cleared explicitly by calling err_clear(). -The only time C code should call err_clear() is if it doesn't want to -pass the error on to the interpreter but wants to handle it completely -by itself (e.g. by trying something else or pretending nothing -happened). +exception condition must be cleared explicitly by calling +\code{err_clear()}. The only time C code should call +\code{err_clear()} is if it doesn't want to pass the error on to the +interpreter but wants to handle it completely by itself (e.g. by +trying something else or pretending nothing happened). -Finally, the function err_get() gives you both error variables +Finally, the function \code{err_get()} gives you both error variables *and clears them*. Note that even if an error occurred the second one may be NULL. I doubt you will need to use this function. -Note that a failing malloc() call must also be turned into an -exception -- the direct caller of malloc() (or realloc()) must call -err_nomem() and return a failure indicator itself. All the -object-creating functions (newintobject() etc.) already do this, so -only if you call malloc() directly this note is of importance. +Note that a failing \code{malloc()} call must also be turned into an +exception --- the direct caller of \code{malloc()} (or +\code{realloc()}) must call \code{err_nomem()} and return a failure +indicator itself. All the object-creating functions +(\code{newintobject()} etc.) already do this, so only if you call +\code{malloc()} directly this note is of importance. -Also note that, with the important exception of getargs(), functions +Also note that, with the important exception of \code{getargs()}, functions that return an integer status usually use 0 for success and -1 for failure. Finally, be careful about cleaning up garbage (making appropriate -[X]DECREF() calls) when you return an error! +[\code{X}]\code{DECREF()} calls) when you return an error! \section{Back to the example} @@ -186,7 +190,7 @@ bit: It returns NULL (the error indicator for functions of this kind) if an error is detected in the argument list, relying on the exception set -by getargs(). The string value of the argument is now copied to the +by \code{getargs()}. The string value of the argument is now copied to the local variable 'command'. If a Python function is called with multiple arguments, the argument @@ -195,18 +199,18 @@ instance, to explicitly create the tuple containing the arguments first and make the call later. The next statement in posix_system is a call tothe C library function -system(), passing it the string we just got from getargs(): +\code{system()}, passing it the string we just got from \code{getargs()}: \begin{verbatim} sts = system(command); \end{verbatim} Python strings may contain internal null bytes; but if these occur in -this example the rest of the string will be ignored by system(). +this example the rest of the string will be ignored by \code{system()}. -Finally, posix.system() must return a value: the integer status -returned by the C library system() function. This is done by the -function newintobject(), which takes a (long) integer as parameter. +Finally, posix.\code{system()} must return a value: the integer status +returned by the C library \code{system()} function. This is done by the +function \code{newintobject()}, which takes a (long) integer as parameter. \begin{verbatim} return newintobject((long)sts); @@ -223,13 +227,13 @@ this idiom: 'None' is a unique Python object representing 'no value'. It differs from NULL, which means 'error' in most contexts (except when passed as -a function argument -- there it means 'no arguments'). +a function argument --- there it means 'no arguments'). \section{The module's function table} -I promised to show how I made the function posix_system() available to -Python programs. This is shown later in posixmodule.c: +I promised to show how I made the function \code{posix_system()} +available to Python programs. This is shown later in posixmodule.c: \begin{verbatim} static struct methodlist posix_methods[] = { @@ -246,27 +250,27 @@ Python programs. This is shown later in posixmodule.c: } \end{verbatim} -(The actual initposix() is somewhat more complicated, but most +(The actual \code{initposix()} is somewhat more complicated, but most extension modules are indeed as simple as that.) When the Python -program first imports module 'posix', initposix() is called, which -calls initmodule() with specific parameters. This creates a module -object (which is inserted in the table sys.modules under the key -'posix'), and adds built-in-function objects to the newly created -module based upon the table (of type struct methodlist) that was -passed as its second parameter. The function initmodule() returns a -pointer to the module object that it creates, but this is unused here. -It aborts with a fatal error if the module could not be initialized -satisfactorily. +program first imports module 'posix', \code{initposix()} is called, +which calls \code{initmodule()} with specific parameters. This +creates a module object (which is inserted in the table sys.modules +under the key 'posix'), and adds built-in-function objects to the +newly created module based upon the table (of type struct methodlist) +that was passed as its second parameter. The function +\code{initmodule()} returns a pointer to the module object that it +creates, but this is unused here. It aborts with a fatal error if the +module could not be initialized satisfactorily. \section{Calling the module initialization function} There is one more thing to do: telling the Python module to call the -initfoo() function when it encounters an 'import foo' statement. +\code{initfoo()} function when it encounters an 'import foo' statement. This is done in the file config.c. This file contains a table mapping module names to parameterless void function pointers. You need to add -a declaration of initfoo() somewhere early in the file, and a line -saying +a declaration of \code{initfoo()} somewhere early in the file, and a +line saying \begin{verbatim} {"foo", initfoo}, @@ -274,12 +278,12 @@ saying to the initializer for inittab[]. It is conventional to include both the declaration and the initializer line in preprocessor commands -\verb\#ifdef USE_FOO\ / \verb\#endif\, to make it easy to turn the foo -extension on or off. Note that the Macintosh version uses a different -configuration file, distributed as configmac.c. This strategy may be -extended to other operating system versions, although usually the -standard config.c file gives a pretty useful starting point for a new -config*.c file. +\code{\#ifdef USE_FOO} / \code{\#endif}, to make it easy to turn the +foo extension on or off. Note that the Macintosh version uses a +different configuration file, distributed as configmac.c. This +strategy may be extended to other operating system versions, although +usually the standard config.c file gives a pretty useful starting +point for a new config*.c file. And, of course, I forgot the Makefile. This is actually not too hard, just follow the examples for, say, AMOEBA. Just find all occurrences @@ -287,8 +291,8 @@ of the string AMOEBA in the Makefile and do the same for FOO that's done for AMOEBA... (Note: if you are using dynamic loading for your extension, you don't -need to edit config.c and the Makefile. See "./DYNLOAD" for more info -about this.) +need to edit config.c and the Makefile. See \file{./DYNLOAD} for more +info about this.) \section{Calling Python functions from C} @@ -296,7 +300,7 @@ about this.) The above concentrates on making C functions accessible to the Python programmer. The reverse is also often useful: calling Python functions from C. This is especially the case for libraries that -support so-called "callback" functions. If a C interface makes heavy +support so-called ``callback'' functions. If a C interface makes heavy use of callbacks, the equivalent Python often needs to provide a callback mechanism to the Python programmer; the implementation may require calling the Python callback functions from a C callback. @@ -305,14 +309,14 @@ Other uses are also possible. Fortunately, the Python interpreter is easily called recursively, and there is a standard interface to call a Python function. I won't dwell on how to call the Python parser with a particular string as -input -- if you're interested, have a look at the implementation of -the "-c" command line option in pythonmain.c. +input --- if you're interested, have a look at the implementation of +the \samp{-c} command line option in pythonmain.c. Calling a Python function is easy. First, the Python program must somehow pass you the Python function object. You should provide a function (or some other interface) to do this. When this function is called, save a pointer to the Python function object (be careful to -INCREF it!) in a global variable -- or whereever you see fit. +INCREF it!) in a global variable --- or whereever you see fit. For example, the following function might be part of a module definition: @@ -333,9 +337,9 @@ definition: \end{verbatim} Later, when it is time to call the function, you call the C function -call_object(). This function has two arguments, both pointers to -arbitrary Python objects: the Python function, and the argument. The -argument can be NULL to call the function without arguments. For +\code{call_object()}. This function has two arguments, both pointers +to arbitrary Python objects: the Python function, and the argument. +The argument can be NULL to call the function without arguments. For example: \begin{verbatim} @@ -345,21 +349,22 @@ example: result = call_object(my_callback, (object *)NULL); \end{verbatim} -call_object() returns a Python object pointer: this is -the return value of the Python function. call_object() is -"reference-count-neutral" with respect to its arguments, but the -return value is "new": either it is a brand new object, or it is an +\code{call_object()} returns a Python object pointer: this is +the return value of the Python function. \code{call_object()} is +``reference-count-neutral'' with respect to its arguments, but the +return value is ``new'': either it is a brand new object, or it is an existing object whose reference count has been incremented. So, you should somehow apply DECREF to the result, even (especially!) if you are not interested in its value. Before you do this, however, it is important to check that the return value isn't NULL. If it is, the Python function terminated by raising -an exception. If the C code that called call_object() is called from -Python, it should now return an error indication to its Python caller, -so the interpreter can print a stack trace, or the calling Python code -can handle the exception. If this is not possible or desirable, the -exception should be cleared by calling err_clear(). For example: +an exception. If the C code that called \code{call_object()} is +called from Python, it should now return an error indication to its +Python caller, so the interpreter can print a stack trace, or the +calling Python code can handle the exception. If this is not possible +or desirable, the exception should be cleared by calling +\code{err_clear()}. For example: \begin{verbatim} if (result == NULL) @@ -369,13 +374,14 @@ exception should be cleared by calling err_clear(). For example: \end{verbatim} Depending on the desired interface to the Python callback function, -you may also have to provide an argument to call_object(). In some -cases the argument is also provided by the Python program, through the -same interface that specified the callback function. It can then be -saved and used in the same manner as the function object. In other -cases, you may have to construct a new object to pass as argument. In -this case you must dispose of it as well. For example, if you want to -pass an integral event code, you might use the following code: +you may also have to provide an argument to \code{call_object()}. In +some cases the argument is also provided by the Python program, +through the same interface that specified the callback function. It +can then be saved and used in the same manner as the function object. +In other cases, you may have to construct a new object to pass as +argument. In this case you must dispose of it as well. For example, +if you want to pass an integral event code, you might use the +following code: \begin{verbatim} object *argument; @@ -391,8 +397,8 @@ pass an integral event code, you might use the following code: Note the placement of DECREF(argument) immediately after the call, before the error check! Also note that strictly spoken this code is -not complete: newintobject() may run out of memory, and this should be -checked. +not complete: \code{newintobject()} may run out of memory, and this +should be checked. In even more complicated cases you may want to pass the callback function multiple arguments. To this end you have to construct (and @@ -401,13 +407,15 @@ errror checks and reference count manipulation) are left as an exercise for the reader; most of this is also needed when returning multiple values from a function. -XXX TO DO: explain objects and reference counting. +XXX TO DO: explain objects. + XXX TO DO: defining new object types. -\section{Format strings for getargs()} +\section{Format strings for {\tt getargs()}} -The getargs() function is declared in "modsupport.h" as follows: +The \code{getargs()} function is declared in \file{modsupport.h} as +follows: \begin{verbatim} int getargs(object *arg, char *format, ...); @@ -416,89 +424,85 @@ The getargs() function is declared in "modsupport.h" as follows: The remaining arguments must be addresses of variables whose type is determined by the format string. For the conversion to succeed, the `arg' object must match the format and the format must be exhausted. -Note that while getargs() checks that the Python object really is of -the specified type, it cannot check that the addresses provided in the -call match: if you make mistakes there, your code will probably dump -core. +Note that while \code{getargs()} checks that the Python object really +is of the specified type, it cannot check that the addresses provided +in the call match: if you make mistakes there, your code will probably +dump core. A format string consists of a single `format unit'. A format unit describes one Python object; it is usually a single character or a parenthesized string. The type of a format units is determined from its first character, the `format letter': -'s' (string) - The Python object must be a string object. The C argument - must be a char** (i.e., the address of a character pointer), - and a pointer to the C string contained in the Python object - is stored into it. If the next character in the format string - is \verb\'#'\, another C argument of type int* must be present, and - the length of the Python string (not counting the trailing - zero byte) is stored into it. - -'z' (string or zero, i.e., NULL) - Like 's', but the object may also be None. In this case the - string pointer is set to NULL and if a \verb\'#'\ is present the size - it set to 0. - -'b' (byte, i.e., char interpreted as tiny int) - The object must be a Python integer. The C argument must be a - char*. - -'h' (half, i.e., short) - The object must be a Python integer. The C argument must be a - short*. - -'i' (int) - The object must be a Python integer. The C argument must be - an int*. - -'l' (long) - The object must be a (plain!) Python integer. The C argument - must be a long*. - -'c' (char) - The Python object must be a string of length 1. The C - argument must be a char*. (Don't pass an int*!) - -'f' (float) - The object must be a Python int or float. The C argument must - be a float*. - -'d' (double) - The object must be a Python int or float. The C argument must - be a double*. - -'S' (string object) - The object must be a Python string. The C argument must be an - object** (i.e., the address of an object pointer). The C - program thus gets back the actual string object that was - passed, not just a pointer to its array of characters and its - size as for format character 's'. - -'O' (object) - The object can be any Python object, including None, but not - NULL. The C argument must be an object**. This can be used - if an argument list must contain objects of a type for which - no format letter exist: the caller must then check that it has - the right type. - -'(' (tuple) - The object must be a Python tuple. Following the '(' - character in the format string must come a number of format - units describing the elements of the tuple, followed by a ')' - character. Tuple format units may be nested. (There are no - exceptions for empty and singleton tuples; "()" specifies an - empty tuple and "(i)" a singleton of one integer. Normally - you don't want to use the latter, since it is hard for the - user to specify. - +\begin{description} + +\item[\samp{s} (string)] +The Python object must be a string object. The C argument must be a +char** (i.e. the address of a character pointer), and a pointer to +the C string contained in the Python object is stored into it. If the +next character in the format string is \samp{\#}, another C argument +of type int* must be present, and the length of the Python string (not +counting the trailing zero byte) is stored into it. + +\item[\samp{z} (string or zero, i.e. \code{NULL})] +Like \samp{s}, but the object may also be None. In this case the +string pointer is set to NULL and if a \samp{\#} is present the size +it set to 0. + +\item[\samp{b} (byte, i.e. char interpreted as tiny int)] +The object must be a Python integer. The C argument must be a char*. + +\item[\samp{h} (half, i.e. short)] +The object must be a Python integer. The C argument must be a short*. + +\item[\samp{i} (int)] +The object must be a Python integer. The C argument must be an int*. + +\item[\samp{l} (long)] +The object must be a (plain!) Python integer. The C argument must be +a long*. + +\item[\samp{c} (char)] +The Python object must be a string of length 1. The C argument must +be a char*. (Don't pass an int*!) + +\item[\samp{f} (float)] +The object must be a Python int or float. The C argument must be a +float*. + +\item[\samp{d} (double)] +The object must be a Python int or float. The C argument must be a +double*. + +\item[\samp{S} (string object)] +The object must be a Python string. The C argument must be an +object** (i.e. the address of an object pointer). The C program thus +gets back the actual string object that was passed, not just a pointer +to its array of characters and its size as for format character +\samp{s}. + +\item[\samp{O} (object)] +The object can be any Python object, including None, but not NULL. +The C argument must be an object**. This can be used if an argument +list must contain objects of a type for which no format letter exist: +the caller must then check that it has the right type. + +\item[\samp{(} (tuple)] +The object must be a Python tuple. Following the \samp{(} character +in the format string must come a number of format units describing the +elements of the tuple, followed by a \samp{)} character. Tuple +format units may be nested. (There are no exceptions for empty and +singleton tuples; \samp{()} specifies an empty tuple and \samp{(i)} a +singleton of one integer. Normally you don't want to use the latter, +since it is hard for the user to specify. + +\end{description} More format characters will probably be added as the need arises. It should be allowed to use Python long integers whereever integers are expected, and perform a range check. (A range check is in fact always -necessary for the 'b', 'h' and 'i' format letters, but this is -currently not implemented.) - +necessary for the \samp{b}, \samp{h} and \samp{i} format +letters, but this is currently not implemented.) Some example calls: @@ -533,14 +537,14 @@ Some example calls: \end{verbatim} Note that a format string must consist of a single unit; strings like -\verb\'is'\ and \verb\'(ii)s#'\ are not valid format strings. (But -\verb\'s#'\ is.) +\samp{is} and \samp{(ii)s\#} are not valid format strings. (But +\samp{s\#} is.) - -The getargs() function does not support variable-length argument -lists. In simple cases you can fake these by trying several calls to -getargs() until one succeeds, but you must take care to call -err_clear() before each retry. For example: +The \code{getargs()} function does not support variable-length +argument lists. In simple cases you can fake these by trying several +calls to +\code{getargs()} until one succeeds, but you must take care to call +\code{err_clear()} before each retry. For example: \begin{verbatim} static object *my_method(self, args) object *self, *args; { @@ -561,46 +565,47 @@ err_clear() before each retry. For example: \end{verbatim} (It is possible to think of an extension to the definition of format -strings to accomodate this directly, e.g., placing a '|' in a tuple -might specify that the remaining arguments are optional. getargs() -should then return 1 + the number of variables stored into.) - +strings to accomodate this directly, e.g., placing a \samp{|} in a +tuple might specify that the remaining arguments are optional. +\code{getargs()} should then return one more than the number of +variables stored into.) Advanced users note: If you set the `varargs' flag in the method list for a function, the argument will always be a tuple (the `raw argument list'). In this case you must enclose single and empty argument lists -in parentheses, e.g., "(s)" and "()". +in parentheses, e.g., \samp{(s)} and \samp{()}. -\section{The mkvalue() function} +\section{The {\tt mkvalue()} function} -This function is the counterpart to getargs(). It is declared in -"modsupport.h" as follows: +This function is the counterpart to \code{getargs()}. It is declared +in \file{modsupport.h} as follows: \begin{verbatim} object *mkvalue(char *format, ...); \end{verbatim} -It supports exactly the same format letters as getargs(), but the -arguments (which are input to the function, not output) must not be -pointers, just values. If a byte, short or float is passed to a +It supports exactly the same format letters as \code{getargs()}, but +the arguments (which are input to the function, not output) must not +be pointers, just values. If a byte, short or float is passed to a varargs function, it is widened by the compiler to int or double, so -'b' and 'h' are treated as 'i' and 'f' is treated as 'd'. 'S' is -treated as 'O', 's' is treated as 'z'. \verb\'z#'\ and \verb\'s#'\ -are supported: a second argument specifies the length of the data -(negative means use strlen()). 'S' and 'O' add a reference to their -argument (so you should DECREF it if you've just created it and aren't -going to use it again). - -If the argument for 'O' or 'S' 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, mkvalue() will return NULL but won't -set an exception if one is already set. If no exception is set, -SystemError is set. - -If there is an error in the format string, the SystemError exception -is set, since it is the calling C code's fault, not that of the Python -user who sees the exception. +\samp{b} and \samp{h} are treated as \samp{i} and \samp{f} is +treated as \samp{d}. \samp{S} is treated as \samp{O}, \samp{s} is +treated as \samp{z}. \samp{z\#} and \samp{s\#} are supported: a +second argument specifies the length of the data (negative means use +\code{strlen()}). \samp{S} and \samp{O} add a reference to their +argument (so you should \code{DECREF()} it if you've just created it +and aren't going to use it again). + +If the argument for \samp{O} or \samp{S} 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, \code{mkvalue()} will +return \code{NULL} but won't set an exception if one is already set. +If no exception is set, \code{SystemError} is set. + +If there is an error in the format string, the \code{SystemError} +exception is set, since it is the calling C code's fault, not that of +the Python user who sees the exception. Example: @@ -610,99 +615,124 @@ Example: returns a tuple containing two zeros. (Outer parentheses in the format string are actually superfluous, but you can use them for -compatibility with getargs(), which requires them if more than one -argument is expected.) +compatibility with \code{getargs()}, which requires them if more than +one argument is expected.) + \section{Reference counts} -Here's a useful explanation of INCREF and DECREF by Sjoerd Mullender. +Here's a useful explanation of \code{INCREF()} and \code{DECREF()} +(after an original by Sjoerd Mullender). -Use XINCREF or XDECREF instead of INCREF/DECREF when the argument may -be NULL. +Use \code{XINCREF()} or \code{XDECREF()} instead of \code{INCREF()} / +\code{DECREF()} when the argument may be \code{NULL}. The basic idea is, if you create an extra reference to an object, you -must INCREF it, if you throw away a reference to an object, you must -DECREF it. Functions such as newstringobject, newsizedstringobject, -newintobject, etc. create a reference to an object. If you want to -throw away the object thus created, you must use DECREF. - -If you put an object into a tuple, list, or dictionary, the idea is -that you usually don't want to keep a reference of your own around, so -Python does not INCREF the elements. It does DECREF the old value. +must \code{INCREF()} it, if you throw away a reference to an object, +you must \code{DECREF()} it. Functions such as +\code{newstringobject()}, \code{newsizedstringobject()}, +\code{newintobject()}, etc. create a reference to an object. If you +want to throw away the object thus created, you must use +\code{DECREF()}. + +If you put an object into a tuple or list using \code{settupleitem()} +or \code{setlistitem()}, the idea is that you usually don't want to +keep a reference of your own around, so Python does not +\code{INCREF()} the elements. It does \code{DECREF()} the old value. This means that if you put something into such an object using the -functions Python provides for this, you must INCREF the object if you -want to keep a separate reference to the object around. Also, if you -replace an element, you should INCREF the old element first if you -want to keep it. If you didn't INCREF it before you replaced it, you -are not allowed to look at it anymore, since it may have been freed. - -Returning an object to Python (i.e., when your module function -returns) creates a reference to an object, but it does not change the -reference count. When your module does not keep another reference to -the object, you should not INCREF or DECREF it. When you do keep a -reference around, you should INCREF the object. Also, when you return -a global object such as None, you should INCREF it. - -If you want to return a tuple, you should consider using mkvalue. -Mkvalue creates a new tuple with a reference count of 1 which you can -return. If any of the elements you put into the tuple are objects, -they are INCREFfed by mkvalue. If you don't want to keep references -to those elements around, you should DECREF them after having called -mkvalue. - -Usually you don't have to worry about arguments. They are INCREFfed -before your function is called and DECREFfed after your function -returns. When you keep a reference to an argument, you should INCREF -it and DECREF when you throw it away. Also, when you return an -argument, you should INCREF it, because returning the argument creates -an extra reference to it. - -If you use getargs() to parse the arguments, you can get a reference -to an object (by using "O" in the format string). This object was not -INCREFfed, so you should not DECREF it. If you want to keep the -object, you must INCREF it yourself. - -If you create your own type of objects, you should use NEWOBJ to -create the object. This sets the reference count to 1. If you want -to throw away the object, you should use DECREF. When the reference -count reaches 0, the dealloc function is called. In it, you should -DECREF all object to which you keep references in your object, but you -should not use DECREF on your object. You should use DEL instead. +functions Python provides for this, you must \code{INCREF()} the +object if you also want to keep a separate reference to the object around. +Also, if you replace an element, you should \code{INCREF()} the old +element first if you want to keep it. If you didn't \code{INCREF()} +it before you replaced it, you are not allowed to look at it anymore, +since it may have been freed. + +Returning an object to Python (i.e. when your C function returns) +creates a reference to an object, but it does not change the reference +count. When your code does not keep another reference to the object, +you should not \code{INCREF()} or \code{DECREF()} it (assuming it is a +newly created object). When you do keep a reference around, you +should \code{INCREF()} the object. Also, when you return a global +object such as \code{None}, you should \code{INCREF()} it. + +If you want to return a tuple, you should consider using +\code{mkvalue()}. This function creates a new tuple with a reference +count of 1 which you can return. If any of the elements you put into +the tuple are objects (format codes \samp{O} or \samp{S}), they +are \code{INCREF()}'ed by \code{mkvalue()}. If you don't want to keep +references to those elements around, you should \code{DECREF()} them +after having called \code{mkvalue()}. + +Usually you don't have to worry about arguments. They are +\code{INCREF()}'ed before your function is called and +\code{DECREF()}'ed after your function returns. When you keep a +reference to an argument, you should \code{INCREF()} it and +\code{DECREF()} when you throw it away. Also, when you return an +argument, you should \code{INCREF()} it, because returning the +argument creates an extra reference to it. + +If you use \code{getargs()} to parse the arguments, you can get a +reference to an object (by using \samp{O} in the format string). This +object was not \code{INCREF()}'ed, so you should not \code{DECREF()} +it. If you want to keep the object, you must \code{INCREF()} it +yourself. + +If you create your own type of objects, you should use \code{NEWOBJ()} +to create the object. This sets the reference count to 1. If you +want to throw away the object, you should use \code{DECREF()}. When +the reference count reaches zero, your type's \code{dealloc()} +function is called. In it, you should \code{DECREF()} all object to +which you keep references in your object, but you should not use +\code{DECREF()} on your object. You should use \code{DEL()} instead. + + +\section{Using C++} + +It is possible to write extension modules in C++. Some restrictions +apply: since the main program (the Python interpreter) is compiled and +linked by the C compiler, global or static objects with constructors +cannot be used. All functions that will be called directly or +indirectly (i.e. via function pointers) by the Python interpreter will +have to be declared using \code{extern "C"}; this applies to all +`methods' as well as to the module's initialization function. +It is unnecessary to enclose the Python header files in +\code{extern "C" \{...\}} --- they do this already. + \chapter{Embedding Python in another application} Embedding Python is similar to extending it, but not quite. The difference is that when you extend Python, the main program of the application is still the Python interpreter, while of you embed -Python, the main program may have nothing to do with Python -- +Python, the main program may have nothing to do with Python --- instead, some parts of the application occasionally call the Python interpreter to run some Python code. So if you are embedding Python, you are providing your own main program. One of the things this main program has to do is initialize the Python interpreter. At the very least, you have to call the -function initall(). There are optional calls to pass command line -arguments to Python. Then later you can call the interpreter from any -part of the application. +function \code{initall()}. There are optional calls to pass command +line arguments to Python. Then later you can call the interpreter +from any part of the application. There are several different ways to call the interpreter: you can pass -a string containing Python statements to run_command(), or you can -pass a stdio file pointer and a file name (for identification in error -messages only) to run_script(). You can also call the lower-level -operations described (partly) in the file \verb\/misc/EXTENDING\ -to construct and use Python objects. +a string containing Python statements to \code{run_command()}, or you +can pass a stdio file pointer and a file name (for identification in +error messages only) to \code{run_script()}. You can also call the +lower-level operations described in the previous chapters to construct +and use Python objects. A simple demo of embedding Python can be found in the directory -\verb\/embed/\. +\file{/embed}. + \section{Using C++} It is also possible to embed Python in a C++ program; how this is done exactly will depend on the details of the C++ system used; in general -you will need to write the main program in C++, enclosing the include -files in \verb\"extern "C" { ... }"\, and compile and link this with -the C++ compiler. (There is no need to recompile Python itself with -C++.) +you will need to write the main program in C++, and use the C++ +compiler to compile and link your program. There is no need to +recompile Python itself with C++. \input{ext.ind} diff --git a/Doc/lib.tex b/Doc/lib.tex index bb00ab3..86784da 100644 --- a/Doc/lib.tex +++ b/Doc/lib.tex @@ -7,8 +7,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } diff --git a/Doc/lib/lib.tex b/Doc/lib/lib.tex index bb00ab3..86784da 100644 --- a/Doc/lib/lib.tex +++ b/Doc/lib/lib.tex @@ -7,8 +7,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } diff --git a/Doc/qua.tex b/Doc/qua.tex index b90a921..7cca09d 100644 --- a/Doc/qua.tex +++ b/Doc/qua.tex @@ -6,8 +6,8 @@ Interactively Testing Remote Servers Using the Python Programming Language \author{ Guido van Rossum \\ - CWI, dept. CST; Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} \and Jelke de Boer \\ diff --git a/Doc/ref.tex b/Doc/ref.tex index cf7d30a..7f679d6 100644 --- a/Doc/ref.tex +++ b/Doc/ref.tex @@ -4,8 +4,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } diff --git a/Doc/ref/ref.tex b/Doc/ref/ref.tex index cf7d30a..7f679d6 100644 --- a/Doc/ref/ref.tex +++ b/Doc/ref/ref.tex @@ -4,8 +4,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } diff --git a/Doc/text2latex.py b/Doc/text2latex.py index 3d28431..069155e 100644 --- a/Doc/text2latex.py +++ b/Doc/text2latex.py @@ -1,6 +1,7 @@ import os import sys import regex +import regsub import string import getopt @@ -31,6 +32,9 @@ def process(fi, fo): if fmt: nextline = '\n' line = fmt % string.strip(line) + if '(' in line: + line = regsub.gsub('[a-zA-Z0-9_]+()', + '{\\\\tt \\0}', line) elif inverbatim: if blank.match(line) >= 0 and \ indented.match(nextline) < 0: @@ -43,6 +47,9 @@ def process(fi, fo): fo.write('\\begin{verbatim}\n') if inverbatim: line = string.expandtabs(line, 4) + elif not fmt and '(' in line: + line = regsub.gsub('[a-zA-Z0-9_]+()', + '\\\\code{\\0}', line) fo.write(line) #main() diff --git a/Doc/tools/text2latex.py b/Doc/tools/text2latex.py index 3d28431..069155e 100644 --- a/Doc/tools/text2latex.py +++ b/Doc/tools/text2latex.py @@ -1,6 +1,7 @@ import os import sys import regex +import regsub import string import getopt @@ -31,6 +32,9 @@ def process(fi, fo): if fmt: nextline = '\n' line = fmt % string.strip(line) + if '(' in line: + line = regsub.gsub('[a-zA-Z0-9_]+()', + '{\\\\tt \\0}', line) elif inverbatim: if blank.match(line) >= 0 and \ indented.match(nextline) < 0: @@ -43,6 +47,9 @@ def process(fi, fo): fo.write('\\begin{verbatim}\n') if inverbatim: line = string.expandtabs(line, 4) + elif not fmt and '(' in line: + line = regsub.gsub('[a-zA-Z0-9_]+()', + '\\\\code{\\0}', line) fo.write(line) #main() diff --git a/Doc/tut.tex b/Doc/tut.tex index 3aaeba9..42a01a1 100644 --- a/Doc/tut.tex +++ b/Doc/tut.tex @@ -6,8 +6,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } diff --git a/Doc/tut/tut.tex b/Doc/tut/tut.tex index 3aaeba9..42a01a1 100644 --- a/Doc/tut/tut.tex +++ b/Doc/tut/tut.tex @@ -6,8 +6,8 @@ \author{ Guido van Rossum \\ - Dept. CST, CWI, Kruislaan 413 \\ - 1098 SJ Amsterdam, The Netherlands \\ + Dept. CST, CWI, P.O. Box 94079 \\ + 1090 GB Amsterdam, The Netherlands \\ E-mail: {\tt guido@cwi.nl} } -- cgit v0.12