CPython-内置string类型

typedef struct {
    PyObject_VAR_HEAD
    long ob_shash;        // 字符串hash值(-1表示还未计算)
    int ob_sstate;        // interned状态(0表示未被intern)
    char ob_sval[1];      // 字符数组(ob_size+1，包含结束符)
} PyStringObject;

[Python]
>>> s1 = ‘‘
>>> sys.getsizeof(s1)
29                       # 基础大小(PyStringObject_SIZE)
>>> s2 = ‘abc‘
>>> sys.getsizeof(s2)
32

PyTypeObject PyString_Type = {
    PyVarObject_HEAD_INIT(&PyType_Type, 0)
    "str",
    PyStringObject_SIZE,
    sizeof(char),
    string_dealloc,                          /* tp_dealloc */
    (printfunc)string_print,                 /* tp_print */
    (hashfunc)string_hash,                   /* tp_hash */
    string_methods,                          /* tp_methods */
    ...
};

PyObject * PyString_FromString(const char *str)
{
    register size_t size;
    register PyStringObject *op;

    assert(str != NULL);
    size = strlen(str);
    // (1)保证字符串不超长
    if (size > PY_SSIZE_T_MAX - PyStringObject_SIZE) {
        PyErr_SetString(PyExc_OverflowError, "string is too long for a Python string");
        return NULL;
    }
    // (2)空字符串nullstring
    if (size == 0 && (op = nullstring) != NULL) {
        Py_INCREF(op);
        return (PyObject *)op;
    }
    // (3)单字符串尝试从characters中获取
    if (size == 1 && (op = characters[*str & UCHAR_MAX]) != NULL) {
        Py_INCREF(op);
        return (PyObject *)op;
    }

    // (4)分配PyStringObject对象内存
    op = (PyStringObject *)PyObject_MALLOC(PyStringObject_SIZE + size);
    if (op == NULL)
        return PyErr_NoMemory();
    (void)PyObject_INIT_VAR(op, &PyString_Type, size);
    op->ob_shash = -1;
    op->ob_sstate = SSTATE_NOT_INTERNED;
    // (5)将字符串复制到对象内部的字符数组中
    Py_MEMCPY(op->ob_sval, str, size+1);

    if (size == 0) {
        // (6)长度为0的字符串进行intern操作
        PyObject *t = (PyObject *)op;
        PyString_InternInPlace(&t);
        op = (PyStringObject *)t;
        nullstring = op;
        Py_INCREF(op);
    } else if (size == 1) {
        // (7)长度为1的字符串进行intern操作
        PyObject *t = (PyObject *)op;
        PyString_InternInPlace(&t);
        op = (PyStringObject *)t;
        characters[*str & UCHAR_MAX] = op;
        Py_INCREF(op);
    }
    return (PyObject *) op;
}