python源码阅读笔记之字符串对象

三、字符串对象
在讲字符串对象时，我大致的讲讲int类型的小问题：
1.对象缓冲池的概念，这也是为了避免大量的内存申请释放开销
2.小量的整数实际上都是缓存在一个内存池里[-5,257],其中的每一个整数都是共享的
#define NSMALLPOSINTS           257
#define NSMALLNEGINTS           5
/* References to small integers are saved in this array so that they
   can be shared.
   The integers that are saved are those in the range
   -NSMALLNEGINTS (inclusive) to NSMALLPOSINTS (not inclusive).
*/
3.大整数呢，就是给定内存空间，需要的时候再使用了

还是一样的从注释开始：
/* PyStringObject_SIZE gives the basic size of a string; any memory allocation
   for a string of length n should request PyStringObject_SIZE + n bytes.

   Using PyStringObject_SIZE instead of sizeof(PyStringObject) saves
   3 bytes per string allocation on a typical system.
*/
#define PyStringObject_SIZE (offsetof(PyStringObject, ob_sval) + 1)

因为字符串是不可变对象，所以在C这里都保存着它的基本信息。

在看看2.7里的string类型：
PyTypeObject PyString_Type = {
    PyVarObject_HEAD_INIT(&PyType_Type, 0)
    "str",
    PyStringObject_SIZE,
    sizeof(char),
    string_dealloc,                             /* tp_dealloc */
    (printfunc)string_print,                    /* tp_print */
    0,                                          /* tp_getattr */
    0,                                          /* tp_setattr */
    0,                                          /* tp_compare */
    string_repr,                                /* tp_repr */
    &string_as_number,                          /* tp_as_number */
    &string_as_sequence,                        /* tp_as_sequence */
    &string_as_mapping,                         /* tp_as_mapping */
    (hashfunc)string_hash,                      /* tp_hash */
    0,                                          /* tp_call */
    string_str,                                 /* tp_str */
    PyObject_GenericGetAttr,                    /* tp_getattro */
    0,                                          /* tp_setattro */
    &string_as_buffer,                          /* tp_as_buffer */
    Py_TPFLAGS_DEFAULT | Py_TPFLAGS_CHECKTYPES |
        Py_TPFLAGS_BASETYPE | Py_TPFLAGS_STRING_SUBCLASS |
        Py_TPFLAGS_HAVE_NEWBUFFER,              /* tp_flags */
    string_doc,                                 /* tp_doc */
    0,                                          /* tp_traverse */
    0,                                          /* tp_clear */
    (richcmpfunc)string_richcompare,            /* tp_richcompare */
    0,                                          /* tp_weaklistoffset */
    0,                                          /* tp_iter */
    0,                                          /* tp_iternext */
    string_methods,                             /* tp_methods */
    0,                                          /* tp_members */
    0,                                          /* tp_getset */
    &PyBaseString_Type,                         /* tp_base */
    0,                                          /* tp_dict */
    0,                                          /* tp_descr_get */
    0,                                          /* tp_descr_set */
    0,                                          /* tp_dictoffset */
    0,                                          /* tp_init */
    0,                                          /* tp_alloc */
    string_new,                                 /* tp_new */
    PyObject_Del,                               /* tp_free */
};

结构体定义如下：
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;

在结构体的注释很清楚的告诉我们：这里面包含了四个对象，ob_sval是个一个字符的数组，
保存着字符串，ob_shash牵扯到hash值，与字典有关。
hash的算法如下：
static long
string_hash(PyStringObject *a)
{
    register Py_ssize_t len;
    register unsigned char *p;
    register long x;

#ifdef Py_DEBUG
    assert(_Py_HashSecret_Initialized);
#endif
    if (a->ob_shash != -1)
        return a->ob_shash;
    len = Py_SIZE(a);
    /*
      We make the hash of the empty string be 0, rather than using
      (prefix ^ suffix), since this slightly obfuscates the hash secret
    */
    if (len == 0) {
        a->ob_shash = 0;
        return 0;
    }
    p = (unsigned char *) a->ob_sval;
    x = _Py_HashSecret.prefix;
    x ^= *p << 7;
    while (--len >= 0)
        x = (1000003*x) ^ *p++;
    x ^= Py_SIZE(a);
    x ^= _Py_HashSecret.suffix;
    if (x == -1)
        x = -2;
    a->ob_shash = x;
    return x;
}

这里指的注意的是，在计算过程中使用位运算计算，这是为了栈溢出。

ob_sstate与string的intern机制有关。
具体实现如下：
void
PyString_InternInPlace(PyObject **p)
{
    register PyStringObject *s = (PyStringObject *)(*p);
    PyObject *t;
    if (s == NULL || !PyString_Check(s))
        Py_FatalError("PyString_InternInPlace: strings only please!");
    /* If it's a string subclass, we don't really know what putting
       it in the interned dict might do. */
    if (!PyString_CheckExact(s))
        return;
    if (PyString_CHECK_INTERNED(s))
        return;
    if (interned == NULL) {
        interned = PyDict_New();
        if (interned == NULL) {
            PyErr_Clear(); /* Don't leave an exception */
            return;
        }
    }
    t = PyDict_GetItem(interned, (PyObject *)s);
    if (t) {
        Py_INCREF(t);
        Py_DECREF(*p);
        *p = t;
        return;
    }

    if (PyDict_SetItem(interned, (PyObject *)s, (PyObject *)s) < 0) {
        PyErr_Clear();
        return;
    }
    /* The two references in interned are not counted by refcnt.
       The string deallocator will take care of this */
    Py_REFCNT(s) -= 2;
    PyString_CHECK_INTERNED(s) = SSTATE_INTERNED_MORTAL;
}
在被intern之后的字符串，全局就只会存在一个PyStringObject对象。并且当判断两个字符串相同时，
只需要看PyObject *相同即可。至于引用计数，从注释来看，
    /* The two references in interned are not counted by refcnt.
       The string deallocator will take care of this */
 
具体机理：在一个新的字符串创建的时候，PyStringObject都会创建，然后再会去检查intern机制，
如果interned相同,最后销毁这个temp.

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

    assert(str != NULL);
    size = strlen(str);
    if (size > PY_SSIZE_T_MAX - PyStringObject_SIZE) {
        PyErr_SetString(PyExc_OverflowError,
            "string is too long for a Python string");
        return NULL;
    }
    if (size == 0 && (op = nullstring) != NULL) {
#ifdef COUNT_ALLOCS
        null_strings++;
#endif
        Py_INCREF(op);
        return (PyObject *)op;
    }
    if (size == 1 && (op = characters[*str & UCHAR_MAX]) != NULL) {
#ifdef COUNT_ALLOCS
        one_strings++;
#endif
        Py_INCREF(op);
        return (PyObject *)op;
    }

    /* Inline PyObject_NewVar */
    op = (PyStringObject *)PyObject_MALLOC(PyStringObject_SIZE + size);
    if (op == NULL)
        return PyErr_NoMemory();
    PyObject_INIT_VAR(op, &PyString_Type, size);
    op->ob_shash = -1;
    op->ob_sstate = SSTATE_NOT_INTERNED;
    Py_MEMCPY(op->ob_sval, str, size+1);
    /* share short strings */
    if (size == 0) {
        PyObject *t = (PyObject *)op;
        PyString_InternInPlace(&t);
        op = (PyStringObject *)t;
        nullstring = op;
        Py_INCREF(op);
    } else if (size == 1) {
        PyObject *t = (PyObject *)op;
        PyString_InternInPlace(&t);
        op = (PyStringObject *)t;
        characters[*str & UCHAR_MAX] = op;
        Py_INCREF(op);
    }
    return (PyObject *) op;
}

size > PY_SSIZE_T_MAX - PyStringObject_SIZE会先做判断，决定是否超过内存。
如果是空字符串，nullstring这个会去处理。建立完后，结果如下：
ref  type  ob_size  ob_hash  ob_sstate  ob_sval  字符串 '\0'

在stringobject.c还包含了很多字符串操作，比如split操作：
PyDoc_STRVAR(split__doc__,
"S.split([sep [,maxsplit]]) -> list of strings\n\
\n\
Return a list of the words in the string S, using sep as the\n\
delimiter string.  If maxsplit is given, at most maxsplit\n\
splits are done. If sep is not specified or is None, any\n\
whitespace string is a separator and empty strings are removed\n\
from the result.");

static PyObject *
string_split(PyStringObject *self, PyObject *args)
{
    Py_ssize_t len = PyString_GET_SIZE(self), n;
    Py_ssize_t maxsplit = -1;
    const char *s = PyString_AS_STRING(self), *sub;
    PyObject *subobj = Py_None;

    if (!PyArg_ParseTuple(args, "|On:split", &subobj, &maxsplit))
        return NULL;
    if (maxsplit < 0)
        maxsplit = PY_SSIZE_T_MAX;
    if (subobj == Py_None)
        return 
        _whitespace((PyObject*) self, s, len, maxsplit);
    if (PyString_Check(subobj)) {
        sub = PyString_AS_STRING(subobj);
        n = PyString_GET_SIZE(subobj);
    }
#ifdef Py_USING_UNICODE
    else if (PyUnicode_Check(subobj))
        return PyUnicode_Split((PyObject *)self, subobj, maxsplit);
#endif
    else if (PyObject_AsCharBuffer(subobj, &sub, &n))
        return NULL;

    return stringlib_split((PyObject*) self, s, len, sub, n, maxsplit);
}