python3中采用的是unicode编码方式
typedef struct {
PyObject_HEAD
Py_ssize_t length; /* Number of code points in the string */
Py_hash_t hash; /* Hash value; -1 if not set */
struct {
unsigned int interned:2;
unsigned int kind:3;
unsigned int compact:1;
unsigned int ascii:1;
unsigned int ready:1;
unsigned int :24;
} state;
wchar_t *wstr;
} PyASCIIObject;
typedef struct {
PyASCIIObject _base;
Py_ssize_t utf8_length;
char *utf8;
Py_ssize_t wstr_length;
} PyCompactUnicodeObject;
typedef struct {
PyCompactUnicodeObject _base;
union {
void *any;
Py_UCS1 *latin1;
Py_UCS2 *ucs2;
Py_UCS4 *ucs4;
} data; /* Canonical, smallest-form Unicode buffer */
} PyUnicodeObject;
如何创建一个字符串对象,python提供了很多的API来创建一个字符串对象,这只是其中的一种
PyObject *PyUnicode_FromString(const char *u)
{
size_t size = strlen(u);
if (size > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError, "input too long");
return NULL;
}
return PyUnicode_DecodeUTF8Stateful(u, (Py_ssize_t)size, NULL, NULL);
}
PY_SSIZE_T_MAX是跟平台有关的值,在WIN64系统下数值应该为
4 294 967 295换算一下也就是4GB,而WIN32系统下则为2GB,一般我们是碰不到这个临界值的。
字符串对象的intern机制
PyUnicode_InternInPlace(PyObject **p)
{
PyObject *s = *p;
PyObject *t;
#ifdef Py_DEBUG
assert(s != NULL);
assert(_PyUnicode_CHECK(s));
#else
if (s == NULL || !PyUnicode_Check(s))
return;
#endif
/* If it's a subclass, we don't really know what putting
it in the interned dict might do. */
if (!PyUnicode_CheckExact(s))
return;
i