cpython/Include/stringobject.h

185 lines
6.5 KiB
C
Raw Normal View History

1991-02-19 08:39:46 -04:00
1990-10-14 09:07:46 -03:00
/* String object interface */
#ifndef Py_STRINGOBJECT_H
#define Py_STRINGOBJECT_H
#ifdef __cplusplus
extern "C" {
#endif
#include <stdarg.h>
1990-10-14 09:07:46 -03:00
/*
Type PyStringObject represents a character string. An extra zero byte is
1990-10-14 09:07:46 -03:00
reserved at the end to ensure it is zero-terminated, but a size is
present so strings with null bytes in them can be represented. This
is an immutable object type.
There are functions to create new string objects, to test
an object for string-ness, and to get the
string value. The latter function returns a null pointer
if the object is not of the proper type.
There is a variant that takes an explicit size as well as a
variant that assumes a zero-terminated string. Note that none of the
functions should be applied to nil objects.
*/
/* Caching the hash (ob_shash) saves recalculation of a string's hash value.
Interning strings (ob_sstate) tries to ensure that only one string
object with a given value exists, so equality tests can be one pointer
comparison. This is generally restricted to strings that "look like"
Python identifiers, although the sys.intern() function can be used to force
interning of any string.
Together, these sped the interpreter by up to 20%. */
1990-10-14 09:07:46 -03:00
typedef struct {
PyObject_VAR_HEAD
long ob_shash;
int ob_sstate;
char ob_sval[1];
/* Invariants:
* ob_sval contains space for 'ob_size+1' elements.
* ob_sval[ob_size] == 0.
* ob_shash is the hash of the string or -1 if not computed yet.
* ob_sstate != 0 iff the string object is in stringobject.c's
* 'interned' dictionary; in this case the two references
* from 'interned' to this object are *not counted* in ob_refcnt.
*/
} PyStringObject;
1990-10-14 09:07:46 -03:00
#define SSTATE_NOT_INTERNED 0
#define SSTATE_INTERNED_MORTAL 1
#define SSTATE_INTERNED_IMMORTAL 2
PyAPI_DATA(PyTypeObject) PyBaseString_Type;
PyAPI_DATA(PyTypeObject) PyString_Type;
1990-10-14 09:07:46 -03:00
Merged revisions 53875-53911 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r53899 | neal.norwitz | 2007-02-25 16:52:27 +0100 (Sun, 25 Feb 2007) | 1 line Add more details when releasing interned strings ........ r53900 | neal.norwitz | 2007-02-25 16:53:36 +0100 (Sun, 25 Feb 2007) | 1 line Whitespace only changes ........ r53901 | jeremy.hylton | 2007-02-25 16:57:45 +0100 (Sun, 25 Feb 2007) | 8 lines Fix crash in exec when unicode filename can't be decoded. I can't think of an easy way to test this behavior. It only occurs when the file system default encoding and the interpreter default encoding are different, such that you can open the file but not decode its name. ........ r53902 | jeremy.hylton | 2007-02-25 17:01:58 +0100 (Sun, 25 Feb 2007) | 2 lines Put declarations before code. ........ r53910 | fred.drake | 2007-02-25 18:56:27 +0100 (Sun, 25 Feb 2007) | 3 lines - SF patch #1657613: add documentation for the Element interface - clean up bogus use of the {datadescni} environment everywhere ........ r53911 | neal.norwitz | 2007-02-25 20:44:48 +0100 (Sun, 25 Feb 2007) | 17 lines Variation of patch # 1624059 to speed up checking if an object is a subclass of some of the common builtin types. Use a bit in tp_flags for each common builtin type. Check the bit to determine if any instance is a subclass of these common types. The check avoids a function call and O(n) search of the base classes. The check is done in the various Py*_Check macros rather than calling PyType_IsSubtype(). All the bits are set in tp_flags when the type is declared in the Objects/*object.c files because PyType_Ready() is not called for all the types. Should PyType_Ready() be called for all types? If so and the change is made, the changes to the Objects/*object.c files can be reverted (remove setting the tp_flags). Objects/typeobject.c would also have to be modified to add conditions for Py*_CheckExact() in addition to each the PyType_IsSubtype check. ........
2007-02-25 16:39:11 -04:00
#define PyString_Check(op) \
PyType_FastSubclass((op)->ob_type, Py_TPFLAGS_STRING_SUBCLASS)
#define PyString_CheckExact(op) ((op)->ob_type == &PyString_Type)
1990-10-14 09:07:46 -03:00
2006-02-15 13:27:45 -04:00
PyAPI_FUNC(PyObject *) PyString_FromStringAndSize(const char *, Py_ssize_t);
PyAPI_FUNC(PyObject *) PyString_FromString(const char *);
PyAPI_FUNC(PyObject *) PyString_FromFormatV(const char*, va_list)
Py_GCC_ATTRIBUTE((format(printf, 1, 0)));
PyAPI_FUNC(PyObject *) PyString_FromFormat(const char*, ...)
Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
2006-02-15 13:27:45 -04:00
PyAPI_FUNC(Py_ssize_t) PyString_Size(PyObject *);
PyAPI_FUNC(char *) PyString_AsString(PyObject *);
PyAPI_FUNC(PyObject *) PyString_Repr(PyObject *, int);
PyAPI_FUNC(void) PyString_Concat(PyObject **, PyObject *);
PyAPI_FUNC(void) PyString_ConcatAndDel(PyObject **, PyObject *);
2006-02-15 13:27:45 -04:00
PyAPI_FUNC(int) _PyString_Resize(PyObject **, Py_ssize_t);
PyAPI_FUNC(int) _PyString_Eq(PyObject *, PyObject*);
PyAPI_FUNC(PyObject *) PyString_Format(PyObject *, PyObject *);
PyAPI_FUNC(PyObject *) _PyString_FormatLong(PyObject*, int, int,
int, char**, int*);
2006-02-15 13:27:45 -04:00
PyAPI_FUNC(PyObject *) PyString_DecodeEscape(const char *, Py_ssize_t,
const char *, Py_ssize_t,
const char *);
1990-10-14 09:07:46 -03:00
PyAPI_FUNC(void) PyString_InternInPlace(PyObject **);
PyAPI_FUNC(void) PyString_InternImmortal(PyObject **);
PyAPI_FUNC(PyObject *) PyString_InternFromString(const char *);
PyAPI_FUNC(void) _Py_ReleaseInternedStrings(void);
/* Use only if you know it's a string */
#define PyString_CHECK_INTERNED(op) (((PyStringObject *)(op))->ob_sstate)
1990-10-14 09:07:46 -03:00
/* Macro, trading safety for speed */
#define PyString_AS_STRING(op) (((PyStringObject *)(op))->ob_sval)
#define PyString_GET_SIZE(op) (((PyStringObject *)(op))->ob_size)
/* _PyString_Join(sep, x) is like sep.join(x). sep must be PyStringObject*,
x must be an iterable object. */
PyAPI_FUNC(PyObject *) _PyString_Join(PyObject *sep, PyObject *x);
/* --- Generic Codecs ----------------------------------------------------- */
/* Create an object by decoding the encoded string s of the
given size. */
PyAPI_FUNC(PyObject*) PyString_Decode(
const char *s, /* encoded string */
2006-02-15 13:27:45 -04:00
Py_ssize_t size, /* size of buffer */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a char buffer of the given size and returns a
Python object. */
PyAPI_FUNC(PyObject*) PyString_Encode(
const char *s, /* string char buffer */
2006-02-15 13:27:45 -04:00
Py_ssize_t size, /* number of chars to encode */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a string object and returns the result as Python
object. */
PyAPI_FUNC(PyObject*) PyString_AsEncodedObject(
PyObject *str, /* string object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a string object and returns the result as Python string
object.
If the codec returns an Unicode object, the object is converted
back to a string using the default encoding.
DEPRECATED - use PyString_AsEncodedObject() instead. */
PyAPI_FUNC(PyObject*) PyString_AsEncodedString(
PyObject *str, /* string object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Decodes a string object and returns the result as Python
object. */
PyAPI_FUNC(PyObject*) PyString_AsDecodedObject(
PyObject *str, /* string object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Decodes a string object and returns the result as Python string
object.
If the codec returns an Unicode object, the object is converted
back to a string using the default encoding.
DEPRECATED - use PyString_AsDecodedObject() instead. */
PyAPI_FUNC(PyObject*) PyString_AsDecodedString(
PyObject *str, /* string object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Provides access to the internal data buffer and size of a string
object or the default encoded version of an Unicode object. Passing
NULL as *len parameter will force the string buffer to be
0-terminated (passing a string with embedded NULL characters will
cause an exception). */
PyAPI_FUNC(int) PyString_AsStringAndSize(
register PyObject *obj, /* string or Unicode object */
register char **s, /* pointer to buffer variable */
2006-02-15 13:27:45 -04:00
register Py_ssize_t *len /* pointer to length variable or NULL
(only possible for 0-terminated
strings) */
);
#ifdef __cplusplus
}
#endif
#endif /* !Py_STRINGOBJECT_H */