Python中的字符串对象(Python 源码剖析第三章)

 1 typedef struct {

 2     PyObject_VAR_HEAD

 3     long ob_shash;

 4     int ob_sstate;

 5     char ob_sval[1];

 6 

 7     /* Invariants:

 8      *     ob_sval contains space for 'ob_size+1' elements.

 9      *     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;

 

 1 PyObject*　PyString_FromString(const char *str)
 2 {
 3     register size_t size;
 4     register PyStringObject *op;
 5 
 6     assert(str != NULL);
 7     size = strlen(str);
 8     if (size > PY_SSIZE_T_MAX - PyStringObject_SIZE) {
 9         PyErr_SetString(PyExc_OverflowError,
10             "string is too long for a Python string");
11         return NULL;
12     }
13     if (size == 0 && (op = nullstring) != NULL) {
14 #ifdef COUNT_ALLOCS
15         null_strings++;
16 #endif
17         Py_INCREF(op);
18         return (PyObject *)op;
19     }
20     if (size == 1 && (op = characters[*str & UCHAR_MAX]) != NULL) {
21 #ifdef COUNT_ALLOCS
22         one_strings++;
23 #endif
24         Py_INCREF(op);
25         return (PyObject *)op;
26     }
27 
28     /* Inline PyObject_NewVar */
29     op = (PyStringObject *)PyObject_MALLOC(PyStringObject_SIZE + size);
30     if (op == NULL)
31         return PyErr_NoMemory();
32     PyObject_INIT_VAR(op, &PyString_Type, size);
33     op->ob_shash = -1;
34     op->ob_sstate = SSTATE_NOT_INTERNED;
35     Py_MEMCPY(op->ob_sval, str, size+1);
36     /* share short strings */
37     if (size == 0) {
38         PyObject *t = (PyObject *)op;
39         PyString_InternInPlace(&t);
40         op = (PyStringObject *)t;
41         nullstring = op;
42         Py_INCREF(op);
43     } else if (size == 1) {
44         PyObject *t = (PyObject *)op;
45         PyString_InternInPlace(&t);
46         op = (PyStringObject *)t;
47         characters[*str & UCHAR_MAX] = op;
48         Py_INCREF(op);
49     }
50     return (PyObject *) op;
51 }